#ai-agents

Git-native tracker where status is derived from repo reality, never typed. Specs in markdown, boards from git, MCP for AI agents, drift auditing for any repo.

Local-first semantic governance for AI agents: contracts, impact, drift, evidence, and verified execution. Codex is the first native integration.

A tiny CLI for onboarding Humans and AI agents into target repositories with machine-readable project boundaries.

Lightweight TUI dashboard for Claude Code token usage, agent sessions, and system resources. Go.

nib — agent, coding agent, and TUI agent development environment

Agent-native Go CLI for local-first video editing: canonical JSON artifacts, safe preview rendering, transcript/framing tools, provider QA, and NLE exchange.

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

MCP server enabling AI agents to make Lightning Network payments

The evidence layer SDK for the agent economy — counter-signed receipts, action records, disputes, and jury-ready evidence envelopes. npm: tersign

Herrscher — shared ABI (proto-only): NATS envelopes, gRPC services, plugin manifest & capability model. Semver.

One MCP server for all web data — search, scrape, crawl, proxy, and AI research in a single npx install. Works with Claude, Cursor, and any MCP client.

In-repo markdown task board for humans and AI agents - a single-binary CLI/TUI, no daemon, git stays yours.

knowmind — CLI + MCP-Server für das Gedächtnis Ihrer KI (knowmind.de). npx -y knowmind mcp

Local-first markdown context engine for AI coding agents. Indexes a repo's docs into SQLite (FTS5 + local vectors) and exposes CLI, HTTP, and MCP over one service core. Ships a docs registry, skills/agents sync, and code-to-doc governance.

Опис репозиторію не опубліковано.

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.

The React framework for building agents into real apps — one definition serves humans (streamed HTML, zero client JS) and agents (markdown, JSON, MCP), nothing duplicated. Web-standards core, deploys to Cloudflare Workers.

Online web discovery CLI for AI agents

Multi-agent orchestration for coding CLIs — dispatch tasks to Claude Code, Codex, Kimi, OpenCode, or Gemini workers and block until they actually report back.

Portable, cross-agent memory & workflow for AI coding agents — Claude Code, Codex, Cursor, Devin, and more. Monorepo: memory substrate, the kit (composition root), CLI bridges, and the engine.

A coding-discipline spec for OpenAI's Codex CLI, enforced by native Codex hooks + a rule-hit telemetry loop. Turns an AGENTS.md the model drifts from into a system that holds. Independent of oh-my-codex.

Open-source infrastructure for AI agents — each gets an email address, folder, inbox, and API key. Move files through named inboxes instead of shared cloud credentials; signed receipts and MCP built in. Human email verification can unlock 5 GB transfers, durable storage, outbound email, and an HTTPS app subdomain. One Go binary, MIT.

A read-only, sanitized GitHub mirror of the open source release for @nhtio/adk

Synthia SDKs (npm + PyPI: synthiaresearch) and the synthia CLI — eval your AI agent against simulated users

An agent composition framework that builds stacks and compiles specialized subagents for Claude Code

Go-native, zero-dependency LLM command-output compressor — an embeddable take on rtk (the Rust 'token killer') with lossless-by-default compression and credential redaction.

The verified-brief organ for coding agents — cited, OSV-gated, injection-safe retrieval + package verification.

Опис репозиторію не опубліковано.

Опис репозиторію не опубліковано.

Deterministic, evidence-based build harness for autonomous coding agents — FSM sprint gates, execution-evidence verification, and adversarial critics. Proof, not opinion.