#ai-agents

Git-native typed knowledge + a unified, self-verifying PR view. Deterministic, LLM-free, no datastore.

Open-source agent middleware — shared memory, credential isolation, and schema learning for AI agents. What one agent learns, every agent knows.

No repository description published.

Does your agent earn its context? Static analyzer for AI agent rosters — overlap, harness gaps, context cost.

.gitignore for AI coding agents — tell Claude/Cursor what NOT to read

Track your testing the way git tracks your code. A CLI that enables AI coding agents to manage their testing pipeline with any test framework.

Harness layer of the Nexus funnel/harness split — Go library for one-turn model deliberation with provider abstraction

The little CMS that lives in your repo: edit TypeScript, JSON, and markdown content files in the browser

Phi Longevity MCP Server

AgentAdmit SDK for Go — User-mediated AI agent authorization

Failover proxy for LLM to automatically switch to best available model provider without interruption of your agents

Debugger CLI for AI agents — run, control, and inspect binaries programmatically with structured output for LLM tooling

The Linear CLI for humans and AI agents

MCP server for cricket: calibrated win-probability model, 22k-match ball-by-ball archive, career and matchup records, live scores. No API key required.

MCP proxy: zero-code GCF adoption. Wraps any MCP server, converts JSON to GCF mid-flight. 53-71% fewer tokens. Works with any structured data.

Convert AI-generated Markdown to WhatsApp, Telegram, Discord, Slack and Instagram compatible formats using an Intermediate Representation (IR) in PHP.

No repository description published.

Lightweight CLI coordination journal for AI agent sessions. Per-shard JSONL files with BSD flock for safe concurrent writes. Zero dependencies - Go standard library only.

go vet for file-based AI agent state: integrity checks for memory, instructions, decisions, and contracts

React & React Native decisions with receipts — a continuously verified corpus with a doctor CLI, migration planner, CI review gate, and MCP server for coding agents.

Circuit breaker daemon for AI agent loops

The Zero-Trust Safety & Settlement Rail for Autonomous AI Agents. Sub-10ms deterministic guardrails, key leak defense, and cryptographic Proof-of-Safety attestations via x402 on Base ($0.002).

AI-agent friendly CLI for Exa — neural web search, URL crawling, and deep research from the terminal. Clean JSON output.

AI Repository Standard (ARS) — define portable AI coding knowledge once in .ai/, compose for Cursor, Copilot, Claude Code & Codex. Reference CLI implementation.

Snag web pages like a polite robot with a browser

Embedded long-term memory database for AI agents & LLM apps. Six-layer cognitive architecture, knowledge graph, hybrid BM25 + vector search, sleep-time memory consolidation. One .meh file, zero infrastructure, pure Go.

An unofficial workspace for ElevenLabs

TypeScript SDK + MCP server for Tersign, the evidence layer for the agent economy — counter-signed EIP-712 receipts, hash-chained action and disclosure records, refunds, disputes, venue-ready evidence envelopes. npm: tersign

An AI agent framework that builds itself — multi-model ReAct + tiered cache-friendly context + async multi-agent + XML workflows. CLI & WebUI, zero LangChain.