Works with VS Code Copilot, Cursor, Claude Code/Desktop, Codex, Cline, Zed, Gemini CLI, Goose, OpenCode, and any other MCP-compatible agent.

Why?

AI coding agents waste tokens re-reading files and searching blindly. ABF gives them purpose-built tools that return exactly what they need — in compact, structured responses that preserve context.

Tools

Tool	What it does
`abf_search`	Code search — exact (ripgrep), keyword-ranked, or semantic (embedding-based)
`abf_search_multi`	Run multiple search queries (exact/keyword/semantic) in one call with weighted score merging
`abf_symbols`	Functions, classes, exports in a file (AST-based for TS/JS, regex for Python)
`abf_chunk`	Smart file chunk by symbol name, chunk index, or file overview
`abf_project_overview`	Tech stack, folder structure, key dependencies at a glance
`abf_dependencies`	Import graph — who imports what
`abf_impact`	Find all usages of a symbol across the project
`abf_impact_typed`	AST-aware (ts-morph) impact analysis with classified references (definition/call/import/type_ref/jsx) and confidence levels
`abf_blast_radius`	BFS over reverse-import graph for a file with risk scoring (low/medium/high)
`abf_related_tests`	Heuristically rank test files most likely to cover a file or symbol
`abf_preview_changes`	Read-only preview: diff + symbol/import deltas + risk flags + external usage probe (no writes)
`abf_refactor_plan`	Read-only ordered edit plan for rename/move/extract/split with collision detection
`abf_apply_edit`	Write tool — atomic file write with sha256 hash check (disabled unless `ABF_ENABLE_WRITES=1`)
`abf_diagnostics`	TypeScript diagnostics (errors/warnings) for one file or all tracked TS/JS files
`abf_definition`	Goto-definition via the TypeScript language service — file, line range, and source preview
`abf_hover`	Type signature + JSDoc for an identifier (IDE-style hover)
`abf_call_graph`	Transitive callers/callees of a function or method (TS/JS, ts-morph)
`abf_git`	Git log, blame, diff (recent/staged/unstaged)
`abf_file_summary`	Full-text search across LLM-generated file summaries (FTS5, OR/AND mode)
`abf_conventions`	Detected naming, structure, and formatting conventions
`abf_index`	Index status, rebuild, incremental update, or trigger re-summarization
`abf_ping`	Health check — returns version and project root

Install

npm install -g agentsbestfriend

Prerequisites

Node.js ≥ 20
ripgrep — brew install ripgrep (macOS) / apt install ripgrep (Linux)
git
Ollama (optional) — for summaries & semantic search: ollama.com

Quick Start

abf init

abf init walks you through everything:

Indexes your project — discovers and indexes all files via git ls-files
Generates LLM summaries & embeddings (if Ollama is running) — with live (12/80) progress
Adds .abf/ to .gitignore — prompts before writing
Installs ABF as an MCP server for your agents — you pick which agents (Cursor, VS Code, Claude Code, etc.) and whether to use npx agentsbestfriend start (always latest) or abf start (local install)

Manual Agent Setup

If you prefer to configure manually, add ABF as a stdio MCP server. Using npx is recommended — it always runs the latest published version without requiring a global install:

VS Code / GitHub Copilot (.vscode/mcp.json):

{
  "servers": {
    "abf": {
      "command": "npx",
      "args": ["agentsbestfriend", "start"]
    }
  }
}

Cursor (.cursor/mcp.json):

{
  "mcpServers": {
    "abf": {
      "command": "npx",
      "args": ["agentsbestfriend", "start"]
    }
  }
}

Claude Desktop (claude_desktop_config.json):

{
  "mcpServers": {
    "abf": {
      "command": "npx",
      "args": ["agentsbestfriend", "start"]
    }
  }
}

Set ABF_PROJECT_ROOT in the env block if the agent does not pass its working directory automatically.

CLI Commands

abf start             Start MCP server in stdio mode (used by agents)
abf init [path]       Index project, set up .gitignore entry, install MCP for agents
abf skill [path]      Install or update the ABF workflow skill for your coding agents
abf index [path]      Re-index a project (incremental by default)
abf status [path]     Show index stats
abf config            Interactive configuration editor
abf doctor            Health checks (Node, ripgrep, git, Ollama)
abf portal            Interactive TUI dashboard

How It Works

ABF maintains a lightweight SQLite index (.abf/index.db) inside each project root. The index is built once and updated incrementally — only changed files are re-processed. A file watcher keeps it current as you edit.

Table	Contents
`files`	Paths, hashes, languages, line counts, LLM summaries
`symbols`	Functions, classes, interfaces, types (AST-extracted)
`imports`	Dependency edges between files
`embeddings`	Float32 vectors for semantic search (chunked for large files)
`file_chunks`	Smart chunks aligned to symbol boundaries
`files_fts`	FTS5 full-text index over summaries

Optional: LLM Enrichment

With Ollama running locally, ABF generates file summaries and embeddings:

ollama pull qwen2.5-coder:1.5b    # file summaries
ollama pull nomic-embed-text       # embeddings / semantic search

Both abf init and abf portal → Re-index show live progress:

◆  Generating LLM summaries... (14/80)
◆  Generating embeddings... (28/80)

Large files are automatically split into chunks for embedding — no context-length errors.

Without Ollama, all tools still work normally. Semantic search falls back to keyword mode.

Configuration

Global config at ~/.abf/config.json. Edit interactively with abf config or via abf portal.

{
  "llm": {
    "provider": "ollama",
    "ollama": {
      "baseUrl": "http://localhost:11434",
      "summaryModel": "qwen2.5-coder:1.5b",
      "embeddingModel": "nomic-embed-text"
    }
  },
  "indexing": {
    "autoWatch": true,
    "respectGitignore": true,
    "maxFileSizeKb": 512,
    "excludedPatterns": ["*.min.js", "*.min.css", "*.map", "*.lock"]
  },
  "search": {
    "defaultMaxResults": 20
  }
}

Architecture

AgentsBestFriend/
├── packages/
│   ├── core/     Shared logic — DB, config, search, analysis, indexer, LLM
│   ├── server/   MCP server (11 tools)
│   └── cli/      Commander.js CLI + TUI portal
├── turbo.json
└── package.json

Built with Turborepo + pnpm workspaces. Core modules:

Module	Purpose
`@abf/core/db`	Drizzle ORM + SQLite (WAL, FTS5)
`@abf/core/config`	Zod-validated config
`@abf/core/search`	ripgrep, keyword scorer, semantic (cosine similarity)
`@abf/core/analysis`	ts-morph AST, conventions detector, project overview
`@abf/core/indexer`	git ls-files discovery, incremental pipeline, file watcher
`@abf/core/llm`	Ollama client, summary & chunked embedding pipelines
`@abf/core/git`	Git CLI wrapper

Development

# Install dependencies
pnpm install

# Build all packages
pnpm build

# Watch mode
pnpm dev

# Type-check
pnpm type-check

License

MIT

Keywords

FAQs

What is agentsbestfriend?

Is agentsbestfriend well maintained?

Package last updated on 22 Apr 2026

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.

Install

agentsbestfriend