sigrank - npm Package Compare versions

Comparing version

0.0.204

0.0.205

+1

-1

package.json

		{
		"name": "sigrank",
		"version": "0.0.204",
		"version": "0.0.205",
		"author": "SunrisesIllNeverSee (https://github.com/SunrisesIllNeverSee)",
		@@ -5,0 +5,0 @@ "description": "SigRank MCP server — the yield cascade + live leaderboard as MCP tools any agent can call",

+16

-16

README.md

		@@ -1,4 +0,4 @@
		# SigRank MCP
		# SigRank SignalAF MCP

		> 🏆 SigRank is live: [signalaf.com](https://signalaf.com) — the leaderboard for how
		> 🏆 SigRank SignalAF is live: [signalaf.com](https://signalaf.com) — the leaderboard for how
		> efficiently you use AI, not how much. Run `npx sigrank` to see your cascade now.
		@@ -9,3 +9,3 @@ > _Token counts only. Never your prompts._

		<p><img src="./.github/assets/og-card.png" alt="SigRank — the new standard in AI evaluation & benchmarks" width="800"></p>
		<p><img src="./.github/assets/og-card.png" alt="SigRank SignalAF — the new standard in AI evaluation & benchmarks" width="800"></p>

		@@ -35,3 +35,3 @@ The yield cascade + live leaderboard as MCP tools any agent can call.

		- [The SigRank ecosystem](#the-sigrank-ecosystem)
		- [The SigRank SignalAF ecosystem](#the-sigrank-signalaf-ecosystem)
		- [Quickstart](#quickstart--3-steps-to-the-board)
		@@ -54,3 +54,3 @@ - [Install from GitHub](#install-from-github)
		\| :-----------------------------------------------------------------------------------: \| :-------------------------------------------------------------------------------: \|
		\| [![SigRank leaderboard](./.github/assets/board.png)](https://signalaf.com/board/all) \| [![SigRank operator profile](./.github/assets/profile.png)](https://signalaf.com) \|
		\| [![SigRank SignalAF leaderboard](./.github/assets/board.png)](https://signalaf.com/board/all) \| [![SigRank SignalAF operator profile](./.github/assets/profile.png)](https://signalaf.com) \|
		\| Every operator ranked by Υ Yield — the architecture of the cascade, not raw spend \| Cascade layer, class, and fingerprint — derived from four token counts \|
		@@ -62,3 +62,3 @@

		## The SigRank ecosystem
		## The SigRank SignalAF ecosystem

		@@ -69,3 +69,3 @@ \| Repo \| What it is \| Install \|
		\| [sigrank-app](https://github.com/SunrisesIllNeverSee/sigrank-app) \| The leaderboard — signalaf.com. Privacy-preserving operator profiles, class tiers, board rankings. \| [signalaf.com](https://signalaf.com) \|
		\| [bestuser-router-mcp](https://github.com/SunrisesIllNeverSee/bestuser-router-mcp) \| The intent layer — routes "who is the best AI user?" queries to SigRank's leaderboard. MCP server for AI assistants. \| `npx bestuser-router-mcp` \|
		\| [bestuser-router-mcp](https://github.com/SunrisesIllNeverSee/bestuser-router-mcp) \| The intent layer — routes "who is the best AI user?" queries to SigRank SignalAF's leaderboard. MCP server for AI assistants. \| `npx bestuser-router-mcp` \|
		\| [sigarena](https://github.com/SunrisesIllNeverSee/sigarena) \| The satellite — public LLM operator evals at sigeconomy.com. Read-only leaderboard, SEO/AEO surface. \| [sigeconomy.com](https://sigeconomy.com) \|
		@@ -81,3 +81,3 @@ \| [signaf](https://github.com/SunrisesIllNeverSee/signa) \| The coach — reads your session logs, builds a taste profile, measures ASI, coaches you on token efficiency. \| `npx @burnmydays/signaf` \|
		\| [SIGNOMY](https://signomy.xyz) \| Governed AI agent marketplace where ranked agents form teams, fill slots, run missions, and earn revenue under constitutional protocol. Agents are free. Operators pay. \|
		\| [MO§ES](https://mos2es.com) \| The governance framework that underpins SigRank, SIGNOMY, and all governed agent operations. Structural accountability for agentic systems. \|
		\| [MO§ES](https://mos2es.com) \| The governance framework that underpins SigRank SignalAF, SIGNOMY, and all governed agent operations. Structural accountability for agentic systems. \|

		@@ -136,3 +136,3 @@ ## Quickstart — 3 steps to the board

		SigRank is available on [Smithery](https://smithery.ai/servers/burnmydays/sigrank) as a stdio MCP bundle — one-click install for Claude Desktop, Cursor, and other MCP clients.
		SigRank SignalAF is available on [Smithery](https://smithery.ai/servers/burnmydays/sigrank) as a stdio MCP bundle — one-click install for Claude Desktop, Cursor, and other MCP clients.

		@@ -145,3 +145,3 @@ ### Smithery CLI

		# Connect to SigRank (downloads the MCPB bundle locally)
		# Connect to SigRank SignalAF (downloads the MCPB bundle locally)
		smithery mcp add burnmydays/sigrank --id sigrank
		@@ -168,3 +168,3 @@
		```
		⊙ SigRank CLI v0.0.177
		⊙ SigRank SignalAF CLI v0.0.177

		@@ -214,3 +214,3 @@ Default (no args)
		Some desktop coding agents receive provider usage in API responses but do not
		persist it in their local session files. SigRank can capture those
		persist it in their local session files. SigRank SignalAF can capture those
		provider-reported counts through a manually started loopback proxy:
		@@ -236,3 +236,3 @@
		Anthropic and OpenAI calls are currently grouped under one `proxy` platform row.
		For streamed Chat Completions, SigRank sets OpenAI's
		For streamed Chat Completions, SigRank SignalAF sets OpenAI's
		`stream_options.include_usage=true` so the provider includes the final usage
		@@ -401,3 +401,3 @@ chunk; response chunks are still forwarded immediately.
		\| OpenCode \| ⚠️ `~/.local/share/opencode` \| Data gap — logs store `cost:0` and derive tokens via LiteLLM at runtime; raw token counts not persisted. No pillars readable with current format \|
		\| SigRank proxy \| ✅ `~/.sigrank-mcp/proxy-sessions.jsonl` \| Opt-in native 4-pillar usage reported by Anthropic/OpenAI; same-timestamp records keep the last call; OpenAI cached input is separated from fresh input \|
		\| SigRank SignalAF proxy \| ✅ `~/.sigrank-mcp/proxy-sessions.jsonl` \| Opt-in native 4-pillar usage reported by Anthropic/OpenAI; same-timestamp records keep the last call; OpenAI cached input is separated from fresh input \|
		\| Other (user JSON) \| ✅ `$SIGRANK_OTHER_PATH` \| User-supplied JSON `{ "windows": { "all": {input,output,cacheCreate,cacheRead} } }`; all-time only (no timestamps) \|
		@@ -413,3 +413,3 @@ \| Cursor \| 🔜 \| Chat log path TBD \|

		- Token-only persistence and submission. Local-log adapters read usage metadata only. The optional proxy necessarily handles provider-bound request and response bytes in memory, but never persists their content; it writes only token counts, model/backend metadata, and timestamps. Only token telemetry is submitted to SigRank.
		- Token-only persistence and submission. Local-log adapters read usage metadata only. The optional proxy necessarily handles provider-bound request and response bytes in memory, but never persists their content; it writes only token counts, model/backend metadata, and timestamps. Only token telemetry is submitted to SigRank SignalAF.
		- Local by default. `tokenpull` reads only `~/.claude/projects` (Claude) or `~/.codex` (Codex) on your device. Numbers stay on your machine unless you explicitly submit with a codename.
		@@ -483,3 +483,3 @@ - Background tooling excluded. Memory plugins, observers, summarizers (e.g. `claude-mem`, `mem0`, `observer-sessions`) are filtered from both Claude and Codex reads. `subagents/` are kept — they represent real operator work.

		Contributions welcome. SigRank MCP is built in the open.
		Contributions welcome. SigRank SignalAF MCP is built in the open.

		@@ -486,0 +486,0 @@ - [Contributing guide](./.github/CONTRIBUTING.md)

sigrank - npm Package Compare versions

Improved metrics