#ai-agents

Like Lighthouse for your agent harness - verify your CLAUDE.md/AGENTS.md, skills & hooks are real, then test and measure they actually work. Claude Code + Codex.

Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.

Spec-driven development framework — AI agents that think before they type

ThumbGate Pre-Action Checks derive rules from repeated failures, flag risky tool calls, hard-block detected secret leaks, and block matches in strict mode.

A Semantic Kernel connector that bridges your local Claude Code OAuth session into Microsoft Semantic Kernel — no manual API key management needed.

A modern solution for running untrusted code in Node.js

TypeScript SDK for astrology, Vedic kundli, tarot, numerology, horoscope, I Ching, biorhythm and more. One multi domain API key, fully typed. AI agent and MCP ready.

MiMo Code: Where Models and Agents Co-Evolve

Standalone MCP server for Obsidian vaults — hybrid search, structured memory, tasks, and full vault access for any AI agent

The collaboration layer for your AI workforce. Run a team of AI agents that coordinate over email, share memory, and get better with every task.

A memory of the codebase your AI agent can't get from grep: a persistent call graph, semantic search, and per-symbol review learnings over any repo. Self-hosted MCP server — Go, tree-sitter, Apache AGE.

23 Claude Code plugins: TDD enforcement hooks, git/PR workflows, spec-driven development, code review, project lifecycle, fix-from-error, maintenance automation, context optimization, research, and multi-LLM delegation. 186 skills, 128 commands, 54 agents.

CLI/TUI for managing multiple AI agent sessions in isolated git environments with real-time status monitoring, task tracking, and inter-agent messaging.

Unbounded context. Memory that manages itself. One session, for life. The hippocampus for coding agents, part of CortexKit.

Verifiable agent actions. Every action becomes signed context for the next. Ed25519 signatures, Merkle log proofs, independently verifiable by anyone.

A terminal multiplexer for AI coding agent sessions, each in an isolated git worktree. Go.

Open-source AI governance gateway for EU teams: enforce PII, cost, model, data residency, and tool policies for LLMs and AI agents with signed evidence.

Official SDKs, API clients, and CLI/MCP tools for Daytona, the secure and elastic infrastructure for running AI-generated code

Composable Go interfaces for running AI agent sessions

Receipt Required for AI agents — no receipt, no irreversible action. An open, offline-verifiable authorization-receipt protocol: a named human signs the exact high-risk action (payment, deploy, delete, permissions) before it runs, and anyone can verify it later, trusting no one. Apache-2.0 · formally verified · IETF Internet-Drafts.

The semantic system of record for AI-written software: a graph of entities and relations, not file diffs.

Self-hostable AI agents you can actually leave running — durable crash-resume, governed autonomy, seccomp sandbox, offline-replayable workflows, CI-native eval. Async-Python, YAML-config, multi-provider (OpenAI/Anthropic/Cloudflare), MIT.

A compiler and runtime for multi-agent DAGs across Pi, Codex, Claude Code, OpenCode, and Grok Build — verify before model spend, isolate context, resume, replay, and recompute.

Persistent semantic memory for AI agents — 100% local on Apple Silicon (MLX) or Linux/Ubuntu (CPU). Markdown source of truth, sqlite-vec + BM25 hybrid search, a codegraph-backed knowledge graph, MCP server + CLI. No cloud, no keys.

AI agent sandboxing done right.

Meerkat - A modular, high-performance agent harness built in Rust.

Local MCP server for delegating asynchronous coding jobs between Claude Code, Codex, Cursor Agent, and Pi.

Millisecond microVM sandbox forking for AI agents on Kubernetes. Firecracker VMs that restore from memory snapshots in milliseconds, fork a running VM into N copies, and persist durable, versioned workspaces. Self-hostable, declarative CRDs.

540 security tests for AI agent systems — MCP, A2A, x402/L402, decision governance, benchmark integrity, skill supply chain. AIUC-1 pre-cert, NIST AI 800-2 aligned, MCP tool-poisoning reproduction. v4.9.1

The trust layer for people and AI. Portable identity, context, and authorization that travels.