Code agents

Local observability for AI agent skill usage

AI Harness Doctor — audit, consolidate & guard your repo's AI agent configs (AGENTS.md, CLAUDE.md, .cursorrules, ...) with a checkup→treat→follow-up→efficacy pipeline

Government of Alberta - Nx plugin for AI-agent development tooling.

AIGNE AI Agent exec provider — wraps runAgent/runCodeAgent as AFS exec actions at /dev/ai/agent

🐙 Universal AI Agent Connector - one key, many agents (OpenCode, Hermes)

AI agent scope enforcement for production codebases.

Open Agent Pack — Declaratively manage AI agent infrastructure

CodePipe turns tasks into reviewed pull requests: an AI agent analyzes, implements, and opens a PR under your control.

AgentFeed CLI for sharing privacy-safe AI agent worklogs — never your code.

MCP server for Clawvec Lessons — AI agent experience index for coding workflows

An Enterprise AI Agent Optimization Platform & Context Intelligence Operating System

Architecture as Code for Vue & React — one config compiles into ESLint rules, a handbook, and an AI agent contract.

50,000+ expert AI agent skills for Claude Code, Kilo, Cline, Opencode, Cursor & Windsurf — visual dashboard, single-click install, doctor, export

Scaffold AI agent config (Cursor, GitHub Copilot, Claude Code, OpenCode) into any repo, then hand off to your AI agent to finish setup.

Drop-in AI agent team framework for Claude Code projects

Developer CLI for Lovrabet apps, datasets, pages, SQL, Backend Function, database connections, skills, and AI agent workflows.

Generic WeClawBot audio/voice endpoint control CLI and AI-agent plugin.

Keep your AI agent context small and cheap by managing tool bloat and large outputs.

Local merge request review, step by step. Your AI agent reviews, codesema displays.

Local-first mailbox for intentional AI agent context handoffs.

Maniac - autonomous AI agent CLI (the what the hell agent)

AI Agent Platform — multi-repo agent management based on OpenCode

Claw coder is a local first AI agent that turns local coding small LLMs into powerful AI agents that actually work

Agent Approve plugin for OpenCode - approve or deny AI agent tool calls from your iPhone and Apple Watch

Self-hosted AI agent platform with local RAG, workspace tools, and CLI

SkillRanger is a local-first router and package manager for AI agent skills.

Totem: local-first toolkit that keeps AI-agent work queryable, enforceable, and derivable as plain files in your codebase

Versioned CLI for installing and migrating AI agent toolkits

CLI and MCP server for OmniContext — AI agent project memory layer

CLI tool for running the pen.dev AI agent manipulating .pen design files

Give your AI agent a memory. And a seatbelt.

The package manager and compiler for AI agent skills — write once, run in every coding agent

AI Agent 任务调度系统 — OpenCode 插件 + CLI + Gateway 常驻进程

Open-source AI agent governance for TypeScript: policy, exact one-use approvals, controlled tool execution, and verifiable receipts.


Open-source replica of Work Louder's Codex Micro using a consumer gamepad as the physical AI-agent controller.

ORIRO — a free, on-device-friendly terminal AI agent. Built on the Pi agent harness (used as a library).

.gitignore for AI coding agents — declare files your AI agent must not read.

Linchpin's library of reusable AI agent skills for WordPress projects.

Detect which AI agent is running your code — structured identity (name, version, mode) with evidence, not just a boolean. Reads the AI_AGENT standard (both dialects) and the signals it misses.

142 Cursor AI agent skills, 54 slash commands, 6 subagents, and MCP configs for React/Next.js/Supabase development.

Poper Skills CLI - install AI agent skills for claude-code, codex, copilot

Interactive AI agent using GitHub Copilot SDK with Hyperlight sandboxed JS execution

Package manager for AI agent steering files — npx steering.sh add owner/repo

The static analyzer your AI agent reads — finds production-blocking bugs in vibe-coded apps (CLI, GitHub Action, MCP server).

Run wrud locally with one command - a local-first recorder for AI-agent sessions (tools, models, cost, insights). `npx @wrud/cli`.

Universal AI Agent rules generator - 从单一源生成各 AI 编码助手的规则文件

Expose any API to an LLM agent as two sandboxed MCP tools (search + execute) on Cloudflare Workers.

Model Context Protocol server for Posecode: let any LLM agent validate, ROM-check, and get a render link for a .posecode movement, natively.

AI agent skill for generating dark-themed architecture diagrams as self-contained HTML files. Works with Claude Code, Cursor, Windsurf, and any LLM agent.

npm-installable CLI wrapper for agent-trace, deterministic record and replay for LLM agent HTTP traffic. Forwards straight to the real Python agent-trace CLI. Requires Python 3.10+ and the agent-observability-trace-cli PyPI package.

Governance for AI-written project docs: verify, catch drift, keep them code-grounded, enforce in CI. OKF-compatible, zero-dependency.

Multi-LLM MCP server for Claude Code & Codex — route AI agent work across 20+ low-cost provider buckets with round-robin dispatch and quota-aware fallback.

LLM capture proxy with Anthropic cache_control TTL stamping, vision handoff, concurrency gating, rate limiting, and a live inspection dashboard

AI agent SDK for web pages — embed a chat assistant that edits page data via schema-validated tools. A lighter, framework-agnostic alternative to CopilotKit/LangChain for in-page JSON-editing agents. Vue-bundled; works with DeepSeek, OpenAI, MCP.

Local AI gateway for OpenCode with tool/function calling — use any model via OpenAI, Anthropic, or Gemini API format

Capix Code — decentralized AI coding agent with GPU marketplace

Passively detects when agents make follow-up promises and automatically delivers on them. Cron is for things you plan. Oath Keeper is for things you promise.

面向 Ubuntu 的安全检测/加固/防护 skill，供 Claude Code / Codex 等 AI agent 调用，支持 npm/npx。命令：scan / run / status / harden / prune / fw-log / fw-rules / fw-optimize / fw-plan / fw-monitor / fw-verify / sensor-setup / sensor-collect / sensor-status / sensor-tune / correla

sara-agent - AI Coding Agent

Persistent self-improving agent memory with tree-of-thoughts reasoning: MCTS/beam search, PRM step verification, self-consistency voting, s1 budget forcing, REPL program-aided reasoning, reflexion self-correction, failure classification, experience replay

Compile messy document directories into Karpathy-style llm_wiki knowledge bases — standalone Q&A CLI + Claude Code/Codex skills

General-purpose agent with transport abstraction, state management, and attachment support

Sema — your own Claude Code-grade coding agent, in the terminal.

An opinionated Pi agent configuration. Includes: custom theme, plan mode, artifacts, subagents, LLM council, configurable restrictions, MCP support and a styled UI.

Manage human-curated context assets for LLMs and agents in Git.

Probe any ACP-compatible agent for its capabilities (models, modes, configOptions, prompt capabilities, auth methods, MCP transports). No real prompt required; no token cost.

Keep your LLM wiki honest: a per-claim citation lockfile, drift detection, and code-grounding for Karpathy-style knowledge bases. Scaffolds a fresh wiki or adopts an existing one; agent-agnostic.

정크 컨텍스트 제거 — LLM 에이전트를 위한 보이지 않는 정보 정돈 레이어

Encode JSON → TOON (40-60% token savings for LLMs!)

NexusAgent - A powerful LLM Code Agent with MCP, Skills, and ACP support

Glassray Coach — a fully self-contained local AI-agent trace debugger (OTLP in, dashboard + agent-first CLI out).

Zero Npm Dependencies Agent Framework

In-memory SkeinStore + queue driver for development and tests.

The open-source LangGraph Platform alternative for TypeScript — self-host LangGraph.js agents. A drop-in replacement for the LangGraph CLI (dev/up/build/dockerfile).

Monitor your AI agents in 3 lines of code — tokens, cost, latency, and silent failures

Fully local web research assistant (LangGraph.js port of langchain-ai/local-deep-researcher) - library, CLI and MCP server

Shared, framework-agnostic building blocks for skein-js HTTP adapters — in-memory dev runtime, LangGraph dev-state import, and langgraph.json CORS mapping.

Local-first web intelligence MCP server for AI coding agents

A CLI that uses a DeepAgents documentation agent to generate and maintain an OpenWiki for a codebase.

Installs the LangChain 1.x / LangGraph skill (API quick-reference + selection guide for Agents, RAG, tools, structured output, memory, middleware, LangSmith) into a project's .claude/skills folder.

Drop-in enforcement for AI agents — authorize every tool call through the Queldrex Trust Layer (allow / require approval / deny) before it runs, in code or as an inline MCP gateway. Fail-safe, zero-dependency.

Inkling is a CLI that uses a DeepAgents documentation agent to generate, maintain, export, and validate a living wiki for your codebase.

The Code-First Notifications Workflow SDK.

Point it at your coding-agent session traces (Claude Code, Codex, OpenCode, Gemini, Pi, …) and get failure-mode + efficiency findings. CLI + SDK over the @tangle-network/agent-eval analyst suite — observe live sessions, run your own analysts, redact, and

A beautiful web UI for Claude Code

An interactive coding agent and command line utility for coding tscircuit TSX circuits

OctoCode - AI-powered development tool by Farhan Dhrubo

SPS CLI — AI-driven development pipeline orchestrator

AAS Core: complete local skill discovery, agent-owned selection, stack validation, and planning, backed by 2,028+ agentic skills.

NexusAgentX distribution of the OpenAI Codex CLI.

MongoDB-backed persistent memory provider for the Vercel AI SDK — Session, Semantic, Procedural, Episodic, and Scratchpad memory with Atlas Vector Search.

Free OpenAI API access with your ChatGPT account.

Agent-Nuvira: Multi-agent AI coding CLI — plan, write, review, test, and publish code with local models (Ollama) or cloud APIs (Groq, NVIDIA NIM, Google Gemini, OpenRouter)

AI Coding Agent — CLI and TUI interface with CI automation support (ReAct loop + built-in tools + skill system)

A context-first, model-agnostic coding agent with an auditable terminal workspace.

Synx Connector — the local CLI/daemon that bridges a coding agent (Claude Agent SDK or OpenAI Codex SDK) on your machine to a Synx workspace over an authenticated WebSocket control channel.

TypeScript SDK for the MiMoCode API

UiPath agent skills for Claude Code, Codex, Cursor, Copilot, Gemini and OpenCode — RPA, UI automation, UI testing, coded agents/apps/workflows, and troubleshooting. Distributed as the UiPath Claude Code plugin.

Host-neutral semantic codebase search with embeddings, symbol discovery, and call-graph tooling