@agentmemory/agentmemory
Advanced tools
Persistent memory for AI coding agents, powered by iii-engine's three primitives
Your coding agent remembers everything. No more re-explaining.
Built on iii engine
Persistent memory for Claude Code, GitHub Copilot CLI, Cursor, Gemini CLI, Codex CLI, Hermes, OpenClaw, pi, OpenCode, and any MCP client.
English | 简体中文 | 繁體中文 | 日本語 | 한국어 | Español | Türkçe | Русский | हिन्दी | Português | Français | Deutsch
The gist extends Karpathy's LLM Wiki pattern with confidence scoring, lifecycle, knowledge graphs, and hybrid search: agentmemory is the implementation.
Install • Quick Start • Benchmarks • vs Competitors • Agents • How It Works • MCP • Viewer • iii Console • Powered by iii • Config • API
npm install -g @agentmemory/agentmemory # once — bare `agentmemory` on PATH
# If you hit EACCES on macOS/Linux system Node installs, retry with:
# sudo npm install -g @agentmemory/agentmemory
agentmemory # start the memory server on :3111
agentmemory demo # seed sample sessions + prove recall
agentmemory connect claude-code # wire MCP into your agent (also: copilot-cli, codex, cursor, gemini-cli, ...)
npx skills add rohitg00/agentmemory -y # install 8 native skills so your agent knows when to use the tools
Or via npx (no install):
npx @agentmemory/agentmemory
Heads-up — npx caches per version. If a bare npx @agentmemory/agentmemory serves an older release, force the latest with npx -y @agentmemory/agentmemory@latest, or clear the cache once with rm -rf ~/.npm/_npx (macOS/Linux; on Windows delete %LOCALAPPDATA%\npm-cache\_npx). The first npx run from v0.9.16+ prompts to install globally inline so the bare agentmemory command works everywhere afterwards.
Full options at Quick Start below. Agent-specific wiring at Works with every agent.
agentmemory works with any agent that supports hooks, MCP, or REST API. All agents share the same memory server.
 Claude Code native plugin + 12 hooks + MCP |
 Codex CLI native plugin + 6 hooks + MCP |
 GitHub Copilot CLI MCP + plugin hooks/skills |
 OpenClaw native plugin + MCP |
 Hermes native plugin + MCP |
 pi native plugin + MCP |
 OpenHuman native Memory trait backend |
 Cursor MCP server |
 Gemini CLI MCP server |
 OpenCode 22 hooks + MCP + plugin |
 Cline MCP server |
 Goose MCP server |
 Kilo Code MCP server |
 Aider REST API |
Claude Desktop MCP server |
 Windsurf MCP server |
 Roo Code MCP server | |
 Warp connect + MCP + skills |
Works with any agent that speaks MCP or HTTP. One server, memories shared across all of them.
You explain the same architecture every session. You re-discover the same bugs. You re-teach the same preferences. Built-in memory (CLAUDE.md, .cursorrules) caps out at 200 lines and goes stale. agentmemory fixes this. It silently captures what your agent does, compresses it into searchable memory, and injects the right context when the next session starts. One command. Works across agents.
What changes: Session 1 you set up JWT auth. Session 2 you ask for rate limiting. The agent already knows your auth uses jose middleware in src/middleware/auth.ts, your tests cover token validation, and you chose jose over jsonwebtoken for Edge compatibility. No re-explaining. No copy-pasting. The agent just knows.
npx @agentmemory/agentmemory
New in v0.9.22 — Three new connect adapters (Qwen Code, Antigravity, Kiro),
AGENT_IDmulti-agent isolation with opt-inAGENTMEMORY_AGENT_SCOPE=isolatedfiltering, install ERESOLVE fixed, OpenAI thinking-model output handled, OpenCode auto-context + session creation, viewer graph settles on 1000+ nodes, 22 fixes total. Full notes in CHANGELOG.md.
Retrieval Accuracycoding-agent-life-v1 (in-house corpus, sandbox-reproducible)
100% top-5 hit rate. 2.2× better precision than the grep baseline on identical input. Full per-type breakdown: LongMemEval-S (ICLR 2025, 500 questions)
|
Token Savings
|
Embedding model:
all-MiniLM-L6-v2(local, free, no API key). Full reports:benchmark/LONGMEMEVAL.md,benchmark/QUALITY.md,benchmark/SCALE.md. Competitor comparison:benchmark/COMPARISON.md— agentmemory vs mem0, Letta, Khoj, claude-mem, Hippo.
Reproduce locally: eval/README.md — adapter-pluggable harness for LongMemEval _s (public 500-Q) + coding-agent-life-v1 (in-house 15-session corpus). Grep / vector / agentmemory adapters score side-by-side, NDJSON output, published scorecards land in docs/benchmarks/.
Pairs with codegraph, Understand Anything, and Graphify. Code-graph indexing, multi-agent build pipelines, and broader knowledge graphs across docs / PDFs / images / videos. agentmemory remembers the work; those three projects light up the rest of the context layer. Recipes + question-routing table: docs/recipes/pairings.md.
| agentmemory | mem0 (53K ⭐) | Letta / MemGPT (22K ⭐) | Built-in (CLAUDE.md) | |
|---|---|---|---|---|
| Type | Memory engine + MCP server | Memory layer API | Full agent runtime | Static file |
| Retrieval R@5 | 95.2% | 68.5% (LoCoMo) | 83.2% (LoCoMo) | N/A (grep) |
| Auto-capture | 12 hooks (zero manual effort) | Manual add() calls | Agent self-edits | Manual editing |
| Search | BM25 + Vector + Graph (RRF fusion) | Vector + Graph | Vector (archival) | Loads everything into context |
| Multi-agent | MCP + REST + leases + signals | API (no coordination) | Within Letta runtime only | Per-agent files |
| Framework lock-in | None (any MCP client) | None | High (must use Letta) | Per-agent format |
| External deps | None (SQLite + iii-engine) | Qdrant / pgvector | Postgres + vector DB | None |
| Memory lifecycle | 4-tier consolidation + decay + auto-forget | Passive extraction | Agent-managed | Manual pruning |
| Token efficiency | ~1,900 tokens/session ($10/yr) | Varies by integration | Core memory in context | 22K+ tokens at 240 obs |
| Real-time viewer | Yes (port 3113) | Cloud dashboard | Cloud dashboard | No |
| Self-hosted | Yes (default) | Optional | Optional | Yes |
Compatibility: this release targets stable iii-sdk ^0.11.0 and iii-engine v0.11.x.
# Terminal 1: start the server
npx @agentmemory/agentmemory
# Terminal 2: seed sample data and see recall in action
npx @agentmemory/agentmemory demo
demo seeds 3 realistic sessions (JWT auth, N+1 query fix, rate limiting) and runs semantic searches against them. You'll see it find "N+1 query fix" when you search "database performance optimization" — keyword matching can't do that.
Open http://localhost:3113 to watch the memory build live.
npx caches per-version. If you ran npx @agentmemory/agentmemory@0.9.14 last week, a bare npx @agentmemory/agentmemory may serve the stale 0.9.14 from ~/.npm/_npx/, not the latest release. Install once and the bare agentmemory command works everywhere:
npm install -g @agentmemory/agentmemory
# If you hit EACCES on macOS/Linux system Node installs, retry with:
# sudo npm install -g @agentmemory/agentmemory
agentmemory # start the server (same as the npx form)
agentmemory stop # tear it down
agentmemory remove # uninstall everything we created
agentmemory connect claude-code # wire one agent
agentmemory doctor # interactive diagnostics + fix prompts
From v0.9.16 onward, the first npx run prompts you to install globally inline — answer Y once and you're set. If you skip, fall back to either of these for a fresh fetch:
npx -y @agentmemory/agentmemory@latest # forces latest from npm (cross-platform)
rm -rf ~/.npm/_npx && npx @agentmemory/agentmemory # macOS/Linux only (POSIX shell)
On Windows / PowerShell, the equivalent cache clear is Remove-Item -Recurse -Force "$env:LOCALAPPDATA\npm-cache\_npx" — the npx -y ...@latest form above is the cross-platform option.
Every session agentmemory records is replayable. Open the viewer, pick the Replay tab, and scrub through the timeline: prompts, tool calls, tool results, and responses render as discrete events with play/pause, speed control (0.5×–4×), and keyboard shortcuts (space to toggle, arrows to step).
Already have older Claude Code JSONL transcripts you want to bring in?
# Import everything under the default ~/.claude/projects
npx @agentmemory/agentmemory import-jsonl
# Or import a single file
npx @agentmemory/agentmemory import-jsonl ~/.claude/projects/-my-project/abc123.jsonl
Imported sessions show up in the Replay picker alongside native ones. Under the hood each entry routes through the mem::replay::load, mem::replay::sessions, and mem::replay::import-jsonl iii functions — no side-channel servers.
Use the maintenance command when you intentionally want to update your local runtime:
npx @agentmemory/agentmemory upgrade
Warning: this command mutates the current workspace/runtime. It can update JavaScript dependencies, may run cargo install iii-engine --force, and may pull Docker images.
Implementation details live in src/cli.ts (see runUpgrade around the src/cli.ts:544-595 region).
Install agentmemory: run `npx @agentmemory/agentmemory` in a separate terminal to start the memory server. Then run `/plugin marketplace add rohitg00/agentmemory` and `/plugin install agentmemory` — the plugin registers all 12 hooks, 8 skills, AND auto-wires the `@agentmemory/mcp` stdio server via its `.mcp.json`, so you get 53 MCP tools (memory_smart_search, memory_save, memory_sessions, memory_governance_delete, etc.) without any extra config step. Verify with `curl http://localhost:3111/agentmemory/health`. The real-time viewer is at http://localhost:3113.
If you wire agentmemory's MCP server through ~/.claude.json directly instead of using /plugin install, Claude Code never resolves ${CLAUDE_PLUGIN_ROOT} and you have to point hook scripts at absolute paths in ~/.claude/settings.json. Those paths typically embed the agentmemory version (e.g. ~/.codex/plugins/cache/agentmemory/agentmemory/0.9.22/scripts/…), so the next upgrade silently breaks every hook (#508).
Workaround:
agentmemory connect claude-code --with-hooks
This merges the same hook commands into ~/.claude/settings.json with absolute paths resolved to the bundled plugin/ directory of the currently installed @agentmemory/agentmemory package. Re-run the command after upgrading agentmemory to refresh the paths. User entries in the same file are preserved; only previous agentmemory entries are replaced. Using the /plugin install path remains the recommended approach.
For remote or protected deployments, launch Claude Code with AGENTMEMORY_URL and AGENTMEMORY_SECRET set. The plugin passes both values through to its bundled MCP server; when AGENTMEMORY_URL is empty, the MCP shim uses http://localhost:3111.
# 1. start the memory server in a separate terminal
npx @agentmemory/agentmemory
# 2. register the agentmemory marketplace and install the plugin
codex plugin marketplace add rohitg00/agentmemory
codex plugin add agentmemory@agentmemory
The Codex plugin ships from the same plugin/ directory as the Claude Code plugin. It registers:
@agentmemory/mcp as an MCP server (proxies all 53 tools when AGENTMEMORY_URL points at a running agentmemory server; falls back to 7 tools locally when no server is reachable)SessionStart, UserPromptSubmit, PreToolUse, PostToolUse, PreCompact, Stop/recall, /remember, /session-history, /forget, /recap, /handoff, /commit-context, /commit-historyCodex's hook engine injects CLAUDE_PLUGIN_ROOT into hook subprocesses (per codex-rs/hooks/src/engine/discovery.rs), so the same hook scripts work across both hosts without duplication. Subagent / SessionEnd / Notification / TaskCompleted / PostToolUseFailure events are Claude-Code-only and are not registered for Codex.
CodexHooks and PluginHooks are both stable + default-enabled in codex-rs/features/src/lib.rs, but Codex Desktop builds currently do not dispatch plugin-local hooks.json (openai/codex#16430). MCP tools still work; only the lifecycle observations are missing.
Until upstream lands the fix, mirror the same hook commands into the global ~/.codex/hooks.json:
agentmemory connect codex --with-hooks
This adds an idempotent block to ~/.codex/hooks.json referencing absolute paths to the bundled scripts (no ${CLAUDE_PLUGIN_ROOT} expansion needed at user-scope). Re-run the same command after upgrading agentmemory to refresh paths. User entries in the same file are preserved; only previous agentmemory entries are replaced.
# MCP-only wiring
agentmemory connect copilot-cli
# Full hooks/skills plugin from the GitHub subdir
copilot plugin install rohitg00/agentmemory:plugin
agentmemory connect copilot-cli merges mcpServers.agentmemory into ~/.copilot/mcp-config.json (or $COPILOT_HOME/mcp-config.json when COPILOT_HOME is set) and preserves existing servers. This adapter is Windows-safe even though other connect adapters still require manual Windows setup. Copilot picks up the MCP server on next launch or after /mcp. Install the plugin as well when you want the full hook/skill experience.
Install agentmemory for OpenClaw. Run `npx @agentmemory/agentmemory` in a separate terminal to start the memory server on localhost:3111. Then add this to my OpenClaw MCP config so agentmemory is available with all 53 memory tools:
{
"mcpServers": {
"agentmemory": {
"command": "npx",
"args": ["-y", "@agentmemory/mcp"],
"env": {
"AGENTMEMORY_URL": "http://localhost:3111"
}
}
}
}
Restart OpenClaw. Verify with `curl http://localhost:3111/agentmemory/health`. Open http://localhost:3113 for the real-time viewer. For deeper memory-slot integration, copy `integrations/openclaw` to `~/.openclaw/extensions/agentmemory` and enable `plugins.slots.memory = "agentmemory"` in `~/.openclaw/openclaw.json`.
Full guide: integrations/openclaw/
Install agentmemory for Hermes. Run `npx @agentmemory/agentmemory` in a separate terminal to start the memory server on localhost:3111. Then add this to ~/.hermes/config.yaml so Hermes can use agentmemory as an MCP server with all 53 memory tools:
mcp_servers:
agentmemory:
command: npx
args: ["-y", "@agentmemory/mcp"]
memory:
provider: agentmemory
Verify with `curl http://localhost:3111/agentmemory/health`. Open http://localhost:3113 for the real-time viewer. For deeper 6-hook memory provider integration (pre-LLM context injection, turn capture, MEMORY.md mirroring, system prompt block), copy integrations/hermes from the agentmemory repo to ~/.hermes/plugins/agentmemory.
Full guide: integrations/hermes/
Start the memory server: npx @agentmemory/agentmemory
npx skills add (50+ agents)agentmemory ships 8 skills (remember, recall, recap, handoff, forget, commit-context, commit-history, session-history) in the Claude-Code-style <dir>/SKILL.md format. The skills CLI by vercel-labs auto-installs them into the calling agent's native skill directory across 50+ agents (Claude Code, Cursor, Cline, Continue, Droid, Warp, Codex, Antigravity, Kiro, OpenCode, Goose, Roo, Trae, Windsurf, and more):
npx skills add rohitg00/agentmemory -y # auto-detects the calling agent
npx skills add rohitg00/agentmemory -y -a warp # explicit agent
npx skills add rohitg00/agentmemory -y -a '*' # install to every installed agent
This is complementary to agentmemory connect <agent>:
agentmemory connect <agent> writes the MCP server config so the tools are available.npx skills add rohitg00/agentmemory installs the skills so the agent knows when to call them.For the few agents the skills CLI doesn't cover yet (Zed v1.3.x and below), drop the 8 SKILL.md files under the agent's native skill directory yourself — same format works everywhere.
The agentmemory entry is the same MCP server block across every host that uses the mcpServers shape (Cursor, Claude Desktop, Cline, Roo Code, Windsurf, Gemini CLI, OpenClaw):
"agentmemory": {
"command": "npx",
"args": ["-y", "@agentmemory/mcp"],
"env": {
"AGENTMEMORY_URL": "${AGENTMEMORY_URL}",
"AGENTMEMORY_SECRET": "${AGENTMEMORY_SECRET}"
}
}
Merge this entry into the existing mcpServers object in the host's config file — don't replace the file. If the file already has other servers, add agentmemory next to them as another key inside mcpServers. If mcpServers is missing entirely, paste the block inside { "mcpServers": { ... } }. The ${VAR} placeholders inherit AGENTMEMORY_URL / AGENTMEMORY_SECRET from the shell at MCP-server launch — unset vars pass empty strings and the shim falls back to http://localhost:3111. One wired entry covers both local and remote (k8s / reverse-proxied) deployments.
| Agent | Config file | Notes |
|---|---|---|
| Cursor | ~/.cursor/mcp.json | Merge into mcpServers. One-click deeplink also available on the website. |
| Claude Desktop | claude_desktop_config.json (Application Support) | Merge into mcpServers. Restart Claude Desktop after editing. |
| Cline / Roo Code / Kilo Code | Cline MCP settings (Settings UI → MCP Servers → Edit) | Same mcpServers block. |
| Windsurf | ~/.codeium/windsurf/mcp_config.json | Same mcpServers block. |
| Gemini CLI | ~/.gemini/settings.json | gemini mcp add agentmemory npx -y @agentmemory/mcp --scope user (auto-merges). |
| GitHub Copilot CLI (MCP only) | ~/.copilot/mcp-config.json | agentmemory connect copilot-cli merges mcpServers.agentmemory; Copilot picks it up on next launch or /mcp. |
| GitHub Copilot CLI (full plugin) | Copilot plugin install | copilot plugin install rohitg00/agentmemory:plugin for the plugin from the GitHub subdir. |
| OpenClaw | OpenClaw MCP config | Same mcpServers block, or use the deeper memory plugin. |
| Codex CLI (MCP only) | .codex/config.toml | TOML shape: codex mcp add agentmemory -- npx -y @agentmemory/mcp, or add [mcp_servers.agentmemory] manually. |
| Codex CLI (full plugin) | Codex plugin marketplace | codex plugin marketplace add rohitg00/agentmemory then codex plugin add agentmemory@agentmemory. Registers MCP + 6 lifecycle hooks (SessionStart, UserPromptSubmit, PreToolUse, PostToolUse, PreCompact, Stop) + 8 skills. On Codex Desktop, also run agentmemory connect codex --with-hooks until openai/codex#16430 lands — plugin hooks are currently silent there. |
| OpenCode (MCP only) | opencode.json | Different shape — top-level mcp key, command as array: {"mcp": {"agentmemory": {"type": "local", "command": ["npx", "-y", "@agentmemory/mcp"], "enabled": true}}}. |
| OpenCode (full plugin) | plugin/opencode/ | 22 auto-capture hooks covering session lifecycle, messages, tools, errors. Two slash commands (/recall, /remember). Copy plugin/opencode/ into your OpenCode workspace and add the plugin entry to opencode.json. See plugin/opencode/README.md for the full hook table + gap analysis. |
| pi | ~/.pi/agent/extensions/agentmemory | Copy integrations/pi and restart pi. |
| Hermes Agent | ~/.hermes/config.yaml | Use the deeper memory provider plugin with memory.provider: agentmemory. |
| Qwen Code | ~/.qwen/settings.json | agentmemory connect qwen writes the standard mcpServers block. Hook payload is field-compatible with Claude Code, so the existing 12-hook scripts work without modification — wire them via the hooks section in the same settings.json. |
| Antigravity (replaces Gemini CLI) | mcp_config.json (in Antigravity's User dir) | agentmemory connect antigravity writes the standard mcpServers block. macOS: ~/Library/Application Support/Antigravity/User/. Linux: ~/.config/Antigravity/User/. Use after the 2026-06-18 Gemini CLI sunset. |
| Kiro | ~/.kiro/settings/mcp.json | agentmemory connect kiro writes the user-level config. Workspace overrides go in .kiro/settings/mcp.json next to your code. |
| Warp | ~/.warp/.mcp.json | agentmemory connect warp writes the standard mcpServers block. Warp also auto-discovers skills from .claude/skills/ — once the Claude Code plugin is installed the 8 agentmemory skills (remember, recall, recap, handoff, forget, commit-context, commit-history, session-history) appear natively in Warp's slash-command palette. |
| Cline (CLI) | ~/.cline/mcp.json | agentmemory connect cline writes the standard mcpServers block. VS Code extension users: paste the same block via Cline Settings → MCP Servers → Edit JSON. |
| Continue.dev | ~/.continue/config.yaml (preferred) or config.json (legacy) | agentmemory connect continue creates config.yaml from scratch when neither exists, or modifies existing config.json. If you already have config.yaml the adapter prints the exact block to paste under mcpServers: — it won't silently rewrite your yaml because preserving comments and anchors safely needs a YAML parser the package doesn't ship. Continue uses array form (not object) for mcpServers. |
| Zed | ~/.config/zed/settings.json | agentmemory connect zed writes under context_servers (Zed's key, NOT mcpServers). Remote MCP servers can be wired via {"url": "..."} instead. |
| Droid (Factory.ai) | ~/.factory/mcp.json | agentmemory connect droid writes the standard mcpServers block. Project-scoped overrides go in <repo>/.factory/mcp.json. The /mcp slash command inside droid lists configured servers. |
| Goose | Goose MCP settings UI | Same mcpServers block — use goose configure → Add Extension → MCP. Direct YAML edit at ~/.config/goose/config.yaml is supported but the schema uses extensions: + cmd (not mcpServers: + command). |
| Aider | n/a | Talk to the REST API directly: curl -X POST http://localhost:3111/agentmemory/smart-search -d '{"query": "auth"}'. |
| Any agent (32+) | n/a | npx skillkit install agentmemory auto-detects the host and merges. |
Sandboxed MCP clients (Flatpak / Snap / restrictive containers) that can't reach the host's localhost: also set "AGENTMEMORY_FORCE_PROXY": "1" in the env block, and point AGENTMEMORY_URL at a route the sandbox can actually reach (e.g. your LAN IP). See #234 for the diagnostic walkthrough.
agentmemory registers its core operations as iii functions (mem::remember, mem::observe, mem::context, mem::smart-search, mem::forget). Any language with an iii SDK can call them directly over ws://localhost:49134 — no separate REST client per language.
pip install iii-sdk # Python
cargo add iii-sdk # Rust
npm install iii-sdk # Node
from iii import register_worker
iii = register_worker("ws://localhost:49134")
iii.connect()
iii.trigger({
"function_id": "mem::smart-search",
"payload": {"project": "demo", "query": "how do tokens refresh"},
})
Worked example: examples/python/ (quickstart + observation/recall flow). REST on :3111 remains available for hosts without an iii runtime.
git clone https://github.com/rohitg00/agentmemory.git && cd agentmemory
npm install && npm run build && npm start
This starts agentmemory with a local iii-engine if iii is already installed, or falls back to Docker Compose if Docker is available. REST, streams, and the viewer bind to 127.0.0.1 by default.
Install iii-engine manually. agentmemory currently pins iii-engine to v0.11.2 — v0.11.6 introduces a new sandbox-everything-via-iii worker add model that agentmemory hasn't been refactored for yet. Pin lifts once the refactor lands. Override with AGENTMEMORY_III_VERSION=<version> if you've migrated to the sandbox model manually.
mkdir -p ~/.local/bin && curl -fsSL https://github.com/iii-hq/iii/releases/download/iii/v0.11.2/iii-aarch64-apple-darwin.tar.gz | tar -xz -C ~/.local/bin && chmod +x ~/.local/bin/iiiaarch64-apple-darwin for x86_64-apple-darwinx86_64-unknown-linux-gnuaarch64-unknown-linux-gnuiii-x86_64-pc-windows-msvc.zip from iii-hq/iii releases v0.11.2, extract iii.exe, add to PATHOr use Docker (the bundled docker-compose.yml pulls iiidev/iii:0.11.2). Full docs: iii.dev/docs.
agentmemory runs on Windows 10/11, but the Node.js package alone isn't enough — you also need the iii-engine runtime (a separate native binary) as a background process. The official upstream installer is a sh script and there is no PowerShell installer or scoop/winget package today, so Windows users have two paths:
Option A — Prebuilt Windows binary (recommended):
# 1. Open https://github.com/iii-hq/iii/releases/tag/iii%2Fv0.11.2 in your browser
# (we pin to v0.11.2 until agentmemory refactors for the new sandbox
# model that engine v0.11.6+ requires)
# 2. Download iii-x86_64-pc-windows-msvc.zip
# (or iii-aarch64-pc-windows-msvc.zip if you're on an ARM machine)
# 3. Extract iii.exe somewhere on PATH, or place it at:
# %USERPROFILE%\.local\bin\iii.exe
# (agentmemory checks that location automatically)
# 4. Verify:
iii --version
# Should print: 0.11.2
# 5. Then run agentmemory as usual:
npx -y @agentmemory/agentmemory
Option B — Docker Desktop:
# 1. Install Docker Desktop for Windows
# 2. Start Docker Desktop and make sure the engine is running
# 3. Run agentmemory — it will auto-start the bundled compose file:
npx -y @agentmemory/agentmemory
Option C — standalone MCP only (no engine): if you only need the MCP tools for your agent and don't need the REST API, viewer, or cron jobs, skip the engine entirely:
npx -y @agentmemory/agentmemory mcp
# or via the shim package:
npx -y @agentmemory/mcp
Diagnostics for Windows: if npx @agentmemory/agentmemory fails, re-run with --verbose to see the actual engine stderr. Common failure modes:
| Symptom | Fix |
|---|---|
iii-engine process started then did not become ready within 15s | Engine crashed on startup — re-run with --verbose, check stderr |
Could not start iii-engine | Neither iii.exe nor Docker is installed. See Option A or B above |
| Port conflict | netstat -ano | findstr :3111 to see what's bound, then kill it or use --port <N> |
| Docker fallback skipped even though Docker is installed | Make sure Docker Desktop is actually running (system tray icon) |
Note: there is no
cargo install iii-engine—iiiis not published to crates.io. The only supported install methods are the prebuilt binary above, the upstreamshinstall script (macOS/Linux only), and the Docker image.
One-click templates for managed hosts. Each one ships a self-contained
Dockerfile that pulls @agentmemory/agentmemory from npm and copies
the iii engine binary in from the official iiidev/iii Docker Hub
image — no pre-built agentmemory image required. Persistent storage
mounts at /data; the first-boot entrypoint overwrites the
npm-bundled iii config (which binds 127.0.0.1) with a deploy-tuned
one that binds 0.0.0.0 and uses absolute /data paths, generates
the HMAC secret, then drops privileges from root to node via
gosu before exec'ing the agentmemory CLI.
Render's one-click deploy button requires render.yaml at the repository root, which we deliberately keep clean. Use the Render Blueprint flow documented in deploy/render/ to point at the in-repo blueprint manually.
Full setup details (HMAC capture, viewer SSH tunnel, rotation, backup,
cost floors) live in deploy/:
deploy/fly — single machine with
auto_stop_machines = "stop"; cheapest idle.deploy/railway — Hobby plan flat fee,
volume in the dashboard.deploy/render — Blueprint flow,
automatic disk snapshots on paid plans.deploy/coolify — self-hosted on your
own VPS via Coolify; same Docker
Compose stack, you own the host and the data.Only port 3111 is published. The viewer on 3113 stays bound to
loopback inside the container — every template's README documents the
SSH-tunnel pattern for reaching it.
Every coding agent forgets everything when the session ends. You waste the first 5 minutes of every session re-explaining your stack. agentmemory runs in the background and eliminates that entirely.
Session 1: "Add auth to the API"
Agent writes code, runs tests, fixes bugs
agentmemory silently captures every tool use
Session ends -> observations compressed into structured memory
Session 2: "Now add rate limiting"
Agent already knows:
- Auth uses JWT middleware in src/middleware/auth.ts
- Tests in test/auth.test.ts cover token validation
- You chose jose over jsonwebtoken for Edge compatibility
Zero re-explaining. Starts working immediately.
Every AI coding agent ships with built-in memory — Claude Code has MEMORY.md, Cursor has notepads, Cline has memory bank. These work like sticky notes. agentmemory is the searchable database behind the sticky notes.
| Built-in (CLAUDE.md) | agentmemory | |
|---|---|---|
| Scale | 200-line cap | Unlimited |
| Search | Loads everything into context | BM25 + vector + graph (top-K only) |
| Token cost | 22K+ at 240 observations | ~1,900 tokens (92% less) |
| Cross-agent | Per-agent files | MCP + REST (any agent) |
| Coordination | None | Leases, signals, actions, routines |
| Observability | Read files manually | Real-time viewer on :3113 |
PostToolUse hook fires
-> SHA-256 dedup (5min window)
-> Privacy filter (strip secrets, API keys)
-> Store raw observation
-> LLM compress -> structured facts + concepts + narrative
-> Vector embedding (6 providers + local)
-> Index in BM25 + vector
Stop / SessionEnd hook fires
-> Summarize session
-> Knowledge graph extraction (if GRAPH_EXTRACTION_ENABLED=true)
-> Slot reflection (if SLOT_REFLECT_ENABLED=true)
SessionStart hook fires
-> Load project profile (top concepts, files, patterns)
-> Hybrid search (BM25 + vector + graph)
-> Token budget (default: 2000 tokens)
-> Inject into conversation
Inspired by how human brains process memory — not unlike sleep consolidation.
| Tier | What | Analogy |
|---|---|---|
| Working | Raw observations from tool use | Short-term memory |
| Episodic | Compressed session summaries | "What happened" |
| Semantic | Extracted facts and patterns | "What I know" |
| Procedural | Workflows and decision patterns | "How to do it" |
Memories decay over time (Ebbinghaus curve). Frequently accessed memories strengthen. Stale memories auto-evict. Contradictions are detected and resolved.
| Hook | Captures |
|---|---|
SessionStart | Project path, session ID |
UserPromptSubmit | User prompts (privacy-filtered) |
PreToolUse | File access patterns + enriched context |
PostToolUse | Tool name, input, output |
PostToolUseFailure | Error context |
PreCompact | Re-injects memory before compaction |
SubagentStart/Stop | Sub-agent lifecycle |
Stop | End-of-session summary |
SessionEnd | Session complete marker |
| Capability | Description |
|---|---|
| Automatic capture | Every tool use recorded via hooks — zero manual effort |
| Semantic search | BM25 + vector + knowledge graph with RRF fusion |
| Memory evolution | Versioning, supersession, relationship graphs |
| Auto-forgetting | TTL expiry, contradiction detection, importance eviction |
| Privacy first | API keys, secrets, <private> tags stripped before storage |
| Self-healing | Circuit breaker, provider fallback chain, health monitoring |
| Claude bridge | Bi-directional sync with MEMORY.md |
| Knowledge graph | Entity extraction + BFS traversal |
| Team memory | Namespaced shared + private across team members |
| Citation provenance | Trace any memory back to source observations |
| Git snapshots | Version, rollback, and diff memory state |
Triple-stream retrieval combining three signals:
| Stream | What it does | When |
|---|---|---|
| BM25 | Stemmed keyword matching with synonym expansion | Always on |
| Vector | Cosine similarity over dense embeddings | Embedding provider configured |
| Graph | Knowledge graph traversal via entity matching | Entities detected in query |
Fused with Reciprocal Rank Fusion (RRF, k=60) and session-diversified (max 3 results per session).
BM25 tokenizes Greek, Cyrillic, Hebrew, Arabic, and accented Latin out of the box. For Chinese / Japanese / Korean memories, install the optional segmenters (npm install @node-rs/jieba tiny-segmenter) to split CJK runs into word-level tokens; without them, agentmemory soft-falls to whole-run tokenization and prints a one-time hint on stderr.
agentmemory auto-detects your provider. For best results, install local embeddings (free):
npm install @xenova/transformers
| Provider | Model | Cost | Notes |
|---|---|---|---|
| Local (recommended) | all-MiniLM-L6-v2 | Free | Offline, +8pp recall over BM25-only |
| Gemini | gemini-embedding-001 | Free tier | 100+ languages, 768/1536/3072 dims (MRL), 2048-token input. Replaces text-embedding-004 (deprecated, shutdown Jan 14, 2026) |
| OpenAI | text-embedding-3-small | $0.02/1M | Highest quality |
| Voyage AI | voyage-code-3 | Paid | Optimized for code |
| Cohere | embed-english-v3.0 | Free trial | General purpose |
| OpenRouter | Any model | Varies | Multi-model proxy |
53 tools, 6 resources, 3 prompts, and 8 skills — the most comprehensive MCP memory toolkit for any agent.
MCP shim vs full server: the published
@agentmemory/mcppackage is a thin shim. It exposes the full 53-tool surface only when it can reach a running agentmemory server viaAGENTMEMORY_URL(proxy mode). With no server reachable, the shim falls back to a 7-tool local set (memory_save,memory_recall,memory_smart_search,memory_sessions,memory_export,memory_audit,memory_governance_delete). TheAGENTMEMORY_TOOLS=core|allenv var is a server-side flag — setting it in the shim'senvblock has no effect. If you see only 7 tools in Cursor / OpenCode / Gemini CLI, startnpx @agentmemory/agentmemory(or the Docker stack) and setAGENTMEMORY_URL=http://localhost:3111.
| Tool | Description |
|---|---|
memory_recall | Search past observations |
memory_compress_file | Compress markdown files while preserving structure |
memory_save | Save an insight, decision, or pattern |
memory_patterns | Detect recurring patterns |
memory_smart_search | Hybrid semantic + keyword search |
memory_file_history | Past observations about specific files |
memory_sessions | List recent sessions |
memory_timeline | Chronological observations |
memory_profile | Project profile (concepts, files, patterns) |
memory_export | Export all memory data |
memory_relations | Query relationship graph |
| Tool | Description |
|---|---|
memory_patterns | Detect recurring patterns |
memory_timeline | Chronological observations |
memory_relations | Query relationship graph |
memory_graph_query | Knowledge graph traversal |
memory_consolidate | Run 4-tier consolidation |
memory_claude_bridge_sync | Sync with MEMORY.md |
memory_team_share | Share with team members |
memory_team_feed | Recent shared items |
memory_audit | Audit trail of operations |
memory_governance_delete | Delete with audit trail |
memory_snapshot_create | Git-versioned snapshot |
memory_action_create | Create work items with dependencies |
memory_action_update | Update action status |
memory_frontier | Unblocked actions ranked by priority |
memory_next | Single most important next action |
memory_lease | Exclusive action leases (multi-agent) |
memory_routine_run | Instantiate workflow routines |
memory_signal_send | Inter-agent messaging |
memory_signal_read | Read messages with receipts |
memory_checkpoint | External condition gates |
memory_mesh_sync | P2P sync between instances |
memory_sentinel_create | Event-driven watchers |
memory_sentinel_trigger | Fire sentinels externally |
memory_sketch_create | Ephemeral action graphs |
memory_sketch_promote | Promote to permanent |
memory_crystallize | Compact action chains |
memory_diagnose | Health checks |
memory_heal | Auto-fix stuck state |
memory_facet_tag | Dimension:value tags |
memory_facet_query | Query by facet tags |
memory_verify | Trace provenance |
| Type | Name | Description |
|---|---|---|
| Resource | agentmemory://status | Health, session count, memory count |
| Resource | agentmemory://project/{name}/profile | Per-project intelligence |
| Resource | agentmemory://memories/latest | Latest 10 active memories |
| Resource | agentmemory://graph/stats | Knowledge graph statistics |
| Prompt | recall_context | Search + return context messages |
| Prompt | session_handoff | Handoff data between agents |
| Prompt | detect_patterns | Analyze recurring patterns |
| Skill | /recall | Search memory |
| Skill | /remember | Save to long-term memory |
| Skill | /session-history | Recent session summaries |
| Skill | /forget | Delete observations/sessions |
Run without the full server — for any MCP client. Either of these works:
npx -y @agentmemory/agentmemory mcp # canonical (always available)
npx -y @agentmemory/mcp # shim package alias
Or add to your agent's MCP config:
Most agents (Cursor, Claude Desktop, Cline, Roo Code, Windsurf, Gemini CLI):
{
"mcpServers": {
"agentmemory": {
"command": "npx",
"args": ["-y", "@agentmemory/mcp"],
"env": {
"AGENTMEMORY_URL": "http://localhost:3111"
}
}
}
}
Merge the agentmemory entry into your host's existing mcpServers object rather than replacing the file. For sandboxed clients that can't reach the host's localhost, add "AGENTMEMORY_FORCE_PROXY": "1" to the env block and set AGENTMEMORY_URL to a route the sandbox can reach.
OpenCode (opencode.json):
{
"mcp": {
"agentmemory": {
"type": "local",
"command": ["npx", "-y", "@agentmemory/mcp"],
"enabled": true
}
},
"plugin": ["./plugins/agentmemory-capture.ts"]
}
Copy the plugin file from the repo:
mkdir -p ~/.config/opencode/plugins
cp plugin/opencode/agentmemory-capture.ts ~/.config/opencode/plugins/
cp plugin/opencode/commands/*.md ~/.config/opencode/commands/
Auto-starts on port 3113. Live observation stream, session explorer, memory browser, knowledge graph visualization, and health dashboard.
open http://localhost:3113
The viewer server binds to 127.0.0.1 by default. The REST-served /agentmemory/viewer endpoint follows the normal AGENTMEMORY_SECRET bearer-token rules. CSP headers use a per-response script nonce and disable inline handler attributes (script-src-attr 'none').
The viewer at :3113 shows what your agent remembered. The iii console shows what your agent did — every memory op as an OpenTelemetry trace, every KV entry editable, every function invocable, every stream tappable. Two windows on the same memory: one product-shaped, one engine-shaped.
Watch a memory_smart_search fire and see the BM25 scan → embedding lookup → RRF fusion → reranker as a waterfall. Edit a stuck consolidation timer in the KV browser. Replay a PostToolUse hook with a tweaked payload. Pin the WebSocket stream and watch observations land live.
agentmemory ships this for free because every function call and trigger fires through iii — nothing custom, nothing to instrument.
Workers page: every connected worker — including agentmemory itself — with PID, function count, runtime, and last-seen.
Already installed. The console ships with iii — no separate installer.
Launch alongside agentmemory:
# agentmemory viewer holds port 3113, so run the console on 3114.
# Engine REST (3111), WebSocket (3112), and bridge (49134) defaults match agentmemory.
iii console --port 3114
Then open http://localhost:3114. Add --enable-flow for the experimental architecture-graph page.
Override engine endpoints only if you've moved them:
iii console --port 3114 \
--engine-port 3111 \
--ws-port 3112 \
--bridge-port 49134
What you can do from the console:
| Page | Use it to |
|---|---|
| Workers | See every connected worker and its live metrics — including the agentmemory worker itself. |
| Functions | Invoke any of agentmemory's functions directly with a JSON payload — handy for testing memory.recall, memory.consolidate, graph.query without wiring a client. |
| Triggers | Replay HTTP, cron, event, and state triggers — fire the consolidation cron manually, retry an HTTP route, emit a state change. |
| States | KV browser with full CRUD — sessions, memory slots, lifecycle timers, embeddings index — edit values in place. |
| Streams | Live WebSocket monitor for memory writes, hook events, and observation updates as they flow through iii streams. |
| Queues | Durable queue topics + dead-letter management. Replay or drop failed embedding / compression jobs. |
| Traces | OpenTelemetry waterfall / flame / service-breakdown views. Filter by trace_id to see exactly which functions, DB calls, and embedding requests a single memory.search produced. |
| Logs | Structured OTEL logs filtered and correlated to trace/span IDs. |
| Config | Runtime configuration — see exactly which workers, providers, and ports your engine is running with. |
| Flow | (Optional, --enable-flow) Interactive architecture graph of every worker, trigger, and stream. |
Traces: waterfall / flame / service breakdown for every memory operation.
Traces are already on:
iii-config.yaml ships with the iii-observability worker enabled (exporter: memory, sampling_ratio: 1.0, metrics + logs). No extra config needed — the moment agentmemory starts, every memory operation emits a trace span and a structured log the console can read.
If you want to export to Jaeger/Honeycomb/Grafana Tempo instead, change exporter: memory to exporter: otlp and set the collector endpoint per iii's observability docs.
Heads-up: no auth is enforced on the console itself — keep it bound to
127.0.0.1(the default) and never expose it publicly.
agentmemory is already a running iii instance. Three primitives — worker, function, trigger — compose the runtime; KV state, streams, and OTEL traces come from iii-state, iii-stream, and iii-observability workers that ship with iii. You didn't install Postgres, Redis, Express, pm2, or Prometheus, because iii replaces them.
That means one more command extends agentmemory with an entire new capability.
iii worker add iii-pubsub # fan memory writes out to every connected instance
iii worker add iii-cron # scheduled consolidation, decay sweeps, snapshot rotation
iii worker add iii-queue # durable retries for embedding + compression jobs
iii worker add iii-observability # OTEL traces on every memory op (default on)
iii worker add iii-sandbox # run recalled code inside an isolated microVM
iii worker add iii-database # swap in a SQL-backed state adapter
iii worker add mcp # generic MCP host alongside the agentmemory MCP
Each iii worker add registers new functions and triggers into the same engine agentmemory is already running on. The viewer and console pick them up immediately — no reload, no new integration, no new container.
iii worker add | What you get on top of agentmemory |
|---|---|
iii-pubsub | Multi-instance memory: every remember fans out, every search reads the union |
iii-cron | Scheduled lifecycle — nightly consolidation, weekly snapshots, decay on a fixed clock |
iii-queue | Durable retries: failed embedding + compression jobs survive restart, no lost observations |
iii-observability | OTEL traces, metrics, logs on every function — wired in iii-config.yaml from day one |
iii-sandbox | Code that came out of memory_recall runs inside a throwaway VM, not your shell |
iii-database | SQL-backed state adapter when you outgrow the in-memory KV defaults |
mcp | Stand up extra MCP servers next to agentmemory's, share the same engine |
Full registry: workers.iii.dev. Every worker there composes through the same primitives agentmemory uses — and the agentmemory you already have is one of them.
| Traditional stack | agentmemory uses |
|---|---|
| Express.js / Fastify | iii HTTP Triggers |
| SQLite / Postgres + pgvector | iii KV State + in-memory vector index |
| SSE / Socket.io | iii Streams (WebSocket) |
| pm2 / systemd | iii engine worker supervision |
| Prometheus / Grafana | iii OTEL + health monitor |
| Custom plugin systems | iii worker add <name> |
118 source files · ~21,800 LOC · 950+ tests · 123 functions · 34 KV scopes — all on three primitives. No agentmemory plugin install. The plugin system is iii itself.
agentmemory auto-detects from your environment. By default, no LLM calls are made unless you configure a provider or explicitly opt in to the Claude subscription fallback.
| Provider | Config | Notes |
|---|---|---|
| No-op (default) | No config needed | LLM-backed compress/summarize is DISABLED. Synthetic BM25 compression + recall still work. See AGENTMEMORY_ALLOW_AGENT_SDK below if you used to rely on the Claude-subscription fallback. |
| Anthropic API | ANTHROPIC_API_KEY | Per-token billing |
| MiniMax | MINIMAX_API_KEY | Anthropic-compatible |
| Gemini | GEMINI_API_KEY | Also enables embeddings |
| OpenRouter | OPENROUTER_API_KEY | Any model |
| OpenAI API | OPENAI_API_KEY | Default gpt-4o-mini, override with OPENAI_MODEL |
| Local (Ollama / LM Studio / vLLM / llama.cpp) | OPENAI_API_KEY=local + OPENAI_BASE_URL=http://localhost:11434/v1 (Ollama) or http://localhost:1234/v1 (LM Studio) + OPENAI_MODEL=<your model> | Anything OpenAI-API-compatible. Zero cost, runs on your hardware. See Local models below. |
| Claude subscription fallback | AGENTMEMORY_ALLOW_AGENT_SDK=true | Opt-in only. Spawns @anthropic-ai/claude-agent-sdk sessions — used to cause unbounded Stop-hook recursion (#149 follow-up) so it is no longer the default. |
agentmemory talks to any OpenAI-API-compatible server, so anything that exposes /v1/chat/completions works without code changes. No paid keys, no cloud, no rate limits — runs entirely on your hardware.
Ollama (default port 11434):
ollama pull qwen2.5-coder:7b # or llama3.2:3b, mistral:7b, etc.
ollama serve
# ~/.agentmemory/.env
OPENAI_API_KEY=ollama # any non-empty string; Ollama ignores it
OPENAI_BASE_URL=http://localhost:11434/v1
OPENAI_MODEL=qwen2.5-coder:7b
LM Studio (default port 1234):
Open LM Studio → Local Server tab → Start Server. Pick any chat model from the picker (Qwen 2.5 Coder, Llama 3.2, DeepSeek, etc.).
# ~/.agentmemory/.env
OPENAI_API_KEY=lmstudio # any non-empty string; LM Studio ignores it
OPENAI_BASE_URL=http://localhost:1234/v1
OPENAI_MODEL=qwen2.5-coder-7b-instruct # match the model name from LM Studio
vLLM / llama.cpp / Text Generation Inference: same shape — point OPENAI_BASE_URL at whatever URL your server exposes, set OPENAI_MODEL to a name your server will accept.
Model picks for memory work: compression and summarization are short tasks (<2K tokens in, <500 tokens out) where a 7B instruct model is plenty. Recommendations:
| Model | Size | Why |
|---|---|---|
qwen2.5-coder:7b | ~4.7 GB | Best at code-shaped sessions; trained on programming + tool-use traces |
llama3.2:3b | ~2 GB | Smallest sane option — fine for compression, weaker for graph extraction |
mistral:7b-instruct | ~4.4 GB | Good general-purpose baseline if you don't want code-specific |
deepseek-r1:7b | ~4.7 GB | Reasoning-tier quality at 7B; slower but cleaner extractions |
Reasoning-class models (o1-style with <think> blocks) can return empty content with a reasoning field your local server may not surface. If extractions come back blank, switch to a non-reasoning model first. The OPENAI_REASONING_EFFORT=none env can also disable thinking on Ollama Cloud thinking models that mirror the OpenAI reasoning schema.
Local embeddings ship out of the box via @xenova/transformers — EMBEDDING_PROVIDER=local (default) gives you BGE-small entirely on-device. No extra config needed.
Background compression runs on every observation, so model choice meaningfully changes monthly spend. Captured workload data: 635 requests / 888K tokens / 35 hours of active use, run against three OpenRouter models at 2026-05-23 pricing.
| Tier | Model | Input / 1M | Output / 1M | Cost for the captured 35h | Notes |
|---|---|---|---|---|---|
| Recommended | deepseek/deepseek-v4-pro | $0.435 | $0.87 | ~$0.46 | Solid compression + summarization quality at ~10× lower cost than Sonnet. |
| Recommended | deepseek/deepseek-chat | $0.27 | $1.10 | ~$0.40 | Older but still fine for compression-only workloads. |
| Recommended | qwen/qwen3-coder | $0.45 | $1.80 | ~$0.55 | Strong code reasoning if your sessions are heavily code-shaped. |
| Premium | anthropic/claude-sonnet-4.6 | $3.00 | $15.00 | ~$5.02 | High quality but expensive for always-on background work. |
| Premium | openai/gpt-4o | $2.50 | $10.00 | ~$4.20 | Similar tier to Sonnet. |
| Avoid | anthropic/claude-opus-4.6 | $15.00 | $75.00 | ~$25+ | Reasoning-class model; massive overspend for compression. |
agentmemory prints a runtime warning when OPENROUTER_MODEL matches a premium-tier pattern. Set AGENTMEMORY_SUPPRESS_COST_WARNING=1 to silence once you've made an informed choice.
Quality vs cost tradeoff for memory work: compression is a summarization task with relatively loose quality bars (the agent re-reads the summary, not the user). DeepSeek-V4-Pro / Qwen3-Coder land within rounding error of Sonnet on this task while costing ~10× less. Save the premium-tier models for queries you read directly.
Sources: OpenRouter pricing for Sonnet 4.6, DeepSeek V4 Pro, DeepSeek pricing notes.
AGENT_ID + AGENTMEMORY_AGENT_SCOPE)In multi-agent setups where several roles share one agentmemory server (architect / developer / reviewer / researcher / support-agent), AGENT_ID tags every write with the role that made it. AGENTMEMORY_AGENT_SCOPE controls whether recall filters by that tag.
TEAM_ID=company
USER_ID=engineering-team
AGENT_ID=architect
AGENTMEMORY_AGENT_SCOPE=isolated # optional; default "shared"
Two modes:
| Mode | Tag writes | Filter recall | When to use |
|---|---|---|---|
shared (default) | yes | no | Cross-agent context with audit trail. Architect can see what developer noted, but every row records who said it. |
isolated | yes | yes | Strict separation. Architect never sees developer's observations / memories / sessions. |
What gets tagged when AGENT_ID is set: Session.agentId, RawObservation.agentId, CompressedObservation.agentId, Memory.agentId. The role flows from api::session::start → mem::observe → mem::compress → KV.
What gets filtered in isolated mode: mem::smart-search, /agentmemory/memories, /agentmemory/observations, /agentmemory/sessions. Each endpoint accepts ?agentId=<role> to override per-request, and ?agentId=* to opt out of the env scope entirely. /memories also accepts ?includeOrphans=true to surface pre-AGENT_ID memories whose agentId is undefined.
Per-call override at the SDK / REST layer: every mutating endpoint (/session/start, /remember) accepts an agentId field in the request body that wins over the env. Useful for runtimes routing many roles through one server process.
When AGENT_ID is unset, memory remains unscoped (legacy behavior, no tags, no filters).
agentmemory + iii-engine bind four ports by default. If a restart fails with port in use, this table tells you which process to look for.
| Port | Process | Purpose | Env override |
|---|---|---|---|
3111 | agentmemory | REST API + MCP HTTP + /agentmemory/health + /agentmemory/livez | III_REST_PORT |
3112 | iii-engine | Internal streams worker (consumed by agentmemory + viewer) | III_STREAMS_PORT |
3113 | agentmemory | Real-time viewer (http://localhost:3113) | AGENTMEMORY_VIEWER_PORT |
49134 | iii-engine | WebSocket — workers register here, OTel telemetry flows over it | III_ENGINE_URL (full URL, default ws://localhost:49134) |
Stale-process cleanup when ports stay bound after a crashed run:
# macOS / Linux — find whatever is on each port and kill it
lsof -i :3111,3112,3113,49134
pkill -f agentmemory || true
pkill -f 'iii ' || true
# Windows
netstat -ano | findstr ":3111 :3112 :3113 :49134"
taskkill /F /PID <pid>
agentmemory stop reaps both the worker and the engine pidfile cleanly on graceful shutdown (#640, #474). The manual cleanup above is only for the post-crash case where neither pidfile is left behind.
Put agentmemory runtime configuration in ~/.agentmemory/.env instead of exporting variables in every shell. If the viewer shows a setup hint like export ANTHROPIC_API_KEY=..., copy it into this file as ANTHROPIC_API_KEY=... without the export prefix, then restart agentmemory.
Process environment variables still work and take precedence over values in the file.
On Windows, the same file lives at %USERPROFILE%\.agentmemory\.env:
New-Item -ItemType Directory -Force $HOME\.agentmemory
notepad $HOME\.agentmemory\.env
To test with a Claude Code Pro/Max subscription instead of an API key, opt in explicitly:
AGENTMEMORY_ALLOW_AGENT_SDK=true
AGENTMEMORY_AUTO_COMPRESS=true
Consolidation (graph nodes, lessons, crystals) is on by default whenever an LLM provider is configured. Explicitly opt out with CONSOLIDATION_ENABLED=false if you want LLM-free operation. Graph extraction is a separate flag:
GRAPH_EXTRACTION_ENABLED=true
# CONSOLIDATION_ENABLED=false # opt out of auto-consolidation
Create ~/.agentmemory/.env:
# LLM provider (pick one — default is the no-op provider: no LLM calls)
# ANTHROPIC_API_KEY=sk-ant-...
# ANTHROPIC_BASE_URL=... # Optional: Anthropic-compatible proxy / Azure
# GEMINI_API_KEY=...
# OPENROUTER_API_KEY=...
# MINIMAX_API_KEY=...
# OPENAI_API_KEY=*** # NOTE: this same key auto-activates BOTH the
# # OpenAI LLM provider (here) AND the OpenAI
# # embedding provider (further below). Set
# # OPENAI_API_KEY_FOR_LLM=false to scope it
# # to embeddings only.
# OPENAI_BASE_URL=https://api.openai.com # Optional: override for Azure / vLLM / LM Studio / proxies
# # Azure: https://<resource>.openai.azure.com/openai/deployments/<deployment>
# # Auto-detected from `.openai.azure.com` hostname; uses
# # api-key header + api-version query param.
# OPENAI_API_VERSION=2024-08-01-preview # Optional: Azure api-version query param
# OPENAI_MODEL=gpt-4o-mini # Optional: default model
# OPENAI_TIMEOUT_MS=60000 # Optional: OpenAI-scoped alias for the outbound fetch
# # timeout. Takes precedence over AGENTMEMORY_LLM_TIMEOUT_MS
# # for back-compat with v0.9.17. New configs should
# # prefer the global AGENTMEMORY_LLM_TIMEOUT_MS below.
# OPENAI_REASONING_EFFORT=none # Optional: "low" | "medium" | "high" | "none"
# # Honored only by OpenAI's reasoning models (o1, o3,
# # gpt-*-reasoning) and providers that mirror that
# # schema (Ollama Cloud thinking models). Standard
# # chat models reject this field with 400. Set to
# # "none" for thinking models that return reasoning
# # but no content.
# OPENAI_API_KEY_FOR_LLM=false # Optional: set to false to skip OpenAI auto-detection
# # for LLM (useful if you only want OpenAI for embeddings)
# Opt-in Claude-subscription fallback (spawns @anthropic-ai/claude-agent-sdk);
# leave OFF unless you understand the Stop-hook recursion risk (#149 follow-up):
# AGENTMEMORY_ALLOW_AGENT_SDK=true
# Embedding provider (auto-detected, or override)
# EMBEDDING_PROVIDER=local
# VOYAGE_API_KEY=...
# OPENAI_API_KEY=sk-...
# OPENAI_BASE_URL=https://api.openai.com # Override for Azure / vLLM / LM Studio / proxies
# OPENAI_EMBEDDING_MODEL=text-embedding-3-small
# OPENAI_EMBEDDING_DIMENSIONS=1536 # Required when the model is not in the known-models table
# Outbound LLM / embedding timeout
# AGENTMEMORY_LLM_TIMEOUT_MS=60000 # Default: 60 000 ms (60 s). Applies to every
# raw-fetch provider (Gemini, OpenRouter, MiniMax,
# OpenAI LLM, OpenAI/Cohere/Voyage/OpenRouter
# embedding). For the OpenAI LLM path, the
# OpenAI-scoped OPENAI_TIMEOUT_MS alias (above)
# takes precedence when set, for back-compat
# with v0.9.17.
# Increase for slow networks or large batch calls;
# decrease to fail-fast on rate-limit holds.
# Search tuning
# BM25_WEIGHT=0.4
# VECTOR_WEIGHT=0.6
# TOKEN_BUDGET=2000
# Auth
# AGENTMEMORY_SECRET=your-secret
# Ports (defaults: 3111 API, 3113 viewer)
# III_REST_PORT=3111
# Features
# AGENTMEMORY_AUTO_COMPRESS=false # OFF by default (#138). When on,
# every PostToolUse hook calls your
# LLM provider to compress the
# observation — expect significant
# token spend on active sessions.
# AGENTMEMORY_SLOTS=false # OFF by default. Editable pinned
# memory slots — persona,
# user_preferences, tool_guidelines,
# project_context, guidance,
# pending_items, session_patterns,
# self_notes. Size-limited; agent
# edits via memory_slot_* tools.
# Pinned slots addressable for
# SessionStart injection.
# AGENTMEMORY_REFLECT=false # OFF by default. Requires SLOTS=on.
# Stop hook fires mem::slot-reflect:
# scans recent observations, auto-
# appends TODOs to pending_items,
# counts patterns in
# session_patterns, records touched
# files in project_context. Fire-
# and-forget; does not block.
# AGENTMEMORY_INJECT_CONTEXT=false # OFF by default (#143). When on:
# - SessionStart may inject ~1-2K
# chars of project context into
# the first turn of each session
# (this is what actually reaches
# the model — Claude Code treats
# SessionStart stdout as context)
# - PreToolUse fires /agentmemory/enrich
# on every file-touching tool call
# (resource cleanup, not a token
# fix — PreToolUse stdout is debug
# log only per Claude Code docs)
# Observations are still captured via
# PostToolUse regardless of this flag.
# GRAPH_EXTRACTION_ENABLED=false
# CONSOLIDATION_ENABLED=false # on by default when an LLM provider is configured
# LESSON_DECAY_ENABLED=true
# OBSIDIAN_AUTO_EXPORT=false
# AGENTMEMORY_EXPORT_ROOT=~/.agentmemory
# CLAUDE_MEMORY_BRIDGE=false
# SNAPSHOT_ENABLED=false
# Team
# TEAM_ID=
# USER_ID=
# TEAM_MODE=private
# Tool visibility: "core" (8 tools, lean fallback) or "all" (53 tools)
# AGENTMEMORY_TOOLS=core
126 endpoints on port 3111. The REST API binds to 127.0.0.1 by default. Protected endpoints require Authorization: Bearer <secret> when AGENTMEMORY_SECRET is set, and mesh sync endpoints require AGENTMEMORY_SECRET on both peers.
| Method | Path | Description |
|---|---|---|
GET | /agentmemory/health | Health check (always public) |
POST | /agentmemory/session/start | Start session + get context |
POST | /agentmemory/session/end | End session |
POST | /agentmemory/observe | Capture observation |
POST | /agentmemory/smart-search | Hybrid search |
POST | /agentmemory/context | Generate context |
POST | /agentmemory/remember | Save to long-term memory |
POST | /agentmemory/forget | Delete observations |
POST | /agentmemory/enrich | File context + memories + bugs |
GET | /agentmemory/profile | Project profile |
GET | /agentmemory/export | Export all data |
POST | /agentmemory/import | Import from JSON |
POST | /agentmemory/graph/query | Knowledge graph query |
POST | /agentmemory/team/share | Share with team |
GET | /agentmemory/audit | Audit trail |
Full endpoint list: src/triggers/api.ts
npm run dev # Hot reload
npm run build # Production build
npm test # 950+ tests
npm run test:integration # API tests (requires running services)
Prerequisites: Node.js >= 20, iii-engine or Docker
FAQs
Persistent memory for AI coding agents, powered by iii-engine's three primitives
The npm package @agentmemory/agentmemory receives a total of 10,163 weekly downloads. As such, @agentmemory/agentmemory popularity was classified as popular.
We found that @agentmemory/agentmemory demonstrated a healthy version release cadence and project activity because the last version was released less than a year ago. It has 1 open source maintainer collaborating on the project.
Did you know?
Socket for GitHub automatically highlights issues in each pull request and monitors the health of all your open source dependencies. Discover the contents of your packages and block harmful activity before you install or update your dependencies.
Research
/Security News
Newer packages in this compromise use native extensions and .pth loaders to execute JavaScript stealers in developer environments.
Research
Socket found 37 malicious PyPI wheels that abuse Python startup hooks to launch a Bun-powered credential stealer tied to Mini Shai-Hulud/Miasma.
Security News
RubyGems and Bundler 4.0.13 introduced an opt-in cooldown feature that delays newly published gems during dependency resolution.