Code agents

Diagnose why your LLM agent failed. Deterministic causal analysis with fix generation.

CLI for installing AGENTS.md, .agents rules, AI coding workflows, and client adapters into software projects.

Debug AI Agents without burning money

AgentForge — multi-agent Telegram bot framework powered by Claude Code

Debug UI for Microsoft Agent Framework with OpenAI-compatible API server.

Debug UI for Microsoft Agent Framework with OpenAI-compatible API server with Visualizations.

Debug UI for Microsoft Agent Framework with OpenAI-compatible API server with Visualizations.

Hyperlight CodeAct integrations for Microsoft Agent Framework.

Monty CodeAct integrations for Microsoft Agent Framework.

Turn plain-English requirements into production-ready multi-agent AI projects (CrewAI, LangGraph, WatsonX Orchestrate).

MCP server for searching Claude Code conversation history via Agent Genesis

Local MCP server + CLI letting multiple MCP clients (Claude Code, OpenCode, Gemini CLI, …) exchange messages over a shared SQLite bus with audit logging.

Drop-in prompt-injection guards for Claude, OpenAI Codex, Hermes, and OpenCLAW agents. Wraps the agent-guard-modernbert-base and agent-guard-deberta-pi-base classifiers on Hugging Face.

CLI tool to explore and inspect past Claude Code and Codex conversation history

One local callback layer for Claude Code and Codex: a macOS-ready CLI for native permission dialogs and notifications, plus a FastAPI-like Python framework

An AI coding agent you can actually trust - with built-in impact preview

Dashboard for monitoring AI coding agent sessions across Claude Code and Codex CLI

Adaptive, file-based project knowledge for AI coding agents

Notion Internal Integration binding for Codex, Claude Code, and other MCP clients.

Local file-backed coordination queue for AI coding agents

Bilingual launcher for AI coding agents (Codex & Claude) with review and loop modes

Reusable self-learning engine for agent workflows

Multi-modal knowledge library with vector and full-text search for text, code, images, and PDFs

The Agent Lifecycle Toolkit (ALTK) is a library of components to help agent builders improve their agent with minimal integration effort and setup.

Multi-Agent Observability SDK for Agent Lighthouse

Convert Claude Code session files to animated gifs and videos. Fork of https://github.com/simonw/claude-code-transcripts.

Detect and debug loops in AI agent execution

MCP server for language intelligence. 53 tools, 30 languages, speculative execution.

Multi-agent task orchestration — delegate work from an orchestrator to specialized sub-agents via a file-based queue.

agentic mafia for modifying

Self-describing local inbox for coding agents

An MCP gateway that aggregates your existing MCP servers and lets you define which servers and individual tools each agent or subagent can access. Solves Claude Code's MCP context window waste where all tool definitions load upfront instead of being discovered when actually needed.

Python SDK for agent-media — generate AI UGC videos with talking heads, B-roll, and subtitles programmatically.

Agentic Memory: Structural Code Graph with Neo4j and MCP

Migrate conversation history between AI coding agents

Nexus is an autonomous CLI coding agent powered by LangGraph and MCP. It plans complex tasks, persists context via SQLite, and securely orchestrates tools. Features specialized Architect/Code modes, real-time metrics, and human-in-the-loop safety for production workflows.

AI agent configuration manager for Claude Code, OpenCode, and Copilot

Cross-platform notifications for long-running agentic CLI tools

Cross-platform notifications for long-running agentic CLI tools

Cross-platform notification system for AI agents (Claude Code, Gemini CLI) with ntfy.sh support

Real-time monitoring and debugging platform for multi-agent AI systems

Orquestrador de Agentes de IA para Desenvolvimento de Software

Modern Python CLI for AgentOS - Streamlined AI-assisted development environment management

Building the infra for Claude Code-native deep research

Runtime pathology detection for AI agents. Diagnoses loops, stalls, oscillation, drift, and silent abandonment.

Local-first diagnostics for MCP and AI coding-agent plugin setups.

Generate and safely update agent-specific instruction files from one engineering policy

Visual browser QA console for AI coding agents — live browser, element selection, source mapping, RTL/a11y/perf audits, and test-fix-verify loops.

A quantitative trading system development framework for A-share stock market

A lightweight Python protocol for agent-oriented documentation

Benchmark how agent-ready a code repository is for LLM coding agents.

MCP server exposing agent-readiness scan, detect, and apply tools to coding agents.

A tool to analyze codebases for AI-Agent Friendliness

Persistent memory and AI briefings for coding agents — drop-in MCP server

Local-first CLI that records every Claude Code and Codex session into a searchable SQLite database

A small runtime to trace, replay and debug multi-tool AI agents.

Local-first CLI for handing coding sessions between agents without losing context

CLI for AI agents to work with Jupyter notebooks via the VS Code bridge

Install Claude Code skills, commands, and agents from GitHub to your project

Cross-session memory and analysis layer for the Rigged tool suite

A CLI to get training data from your own coding agents. Track rollouts and codebase snapshots at every turn. The data can be used for SFT, RL, and Continual Learning.

Local documentation retrieval service for agent-assisted development. Indexes framework docs into typed Knowledge Units and exposes them via CLI and HTTP API.

Synchronize rules and skills across AI coding assistants (Claude Code, Cursor, Gemini, OpenCode, Codex)

Production-grade self-correcting AI agent platform with sandboxed execution

Minimal local Claude Code hook client for command risk scoring

Generate runnable AI agent projects from markdown specs in the agent-deployments repo.

Give your AI Agent eyes to see the entire internet. Search + Read 10+ platforms.

Enterprise Security Monitoring SDK for AI Agents - Secure any AI agent in just 3 lines of code with real-time threat detection, behavioral analysis, and separate logging and threat reporting for comprehensive security monitoring

A web viewer for AI agent coding sessions (Claude Code, Codex, etc.)

Discover and inspect local AI coding agent sessions

A lightweight abstraction for executing CLI coding agents headlessly

Evaluate agent skills before you install them. Think 'npm audit' for SKILL.md files.

Generic installer core for projects that distribute agent skills

CLI to write an agent skill once and deploy it to Claude Code, Codex, Gemini CLI, Cursor and Antigravity

Scan agent skill files for security vulnerabilities. 22 rules across prompt injection, capability escalation, data exfiltration, encoded payloads, and composition risks.

Copy agent skills from git repos into local directories for coding agents

Validate and render portable AI agent skills.

Update your Claude Code, Codex, OpenCode, Amp, ClawdBot skills

Automated skill management for AI coding assistants

Agentic code quality linter — catches slop before it becomes architectural rot

No-code AI agent creation platform with Streamlit UI and FastAPI backend

Install obra/superpowers agentic skills for GitHub Copilot and Claude Code

Bidirectional synchronization tool for custom agents and settings between Claude Code and GitHub Copilot.

Real-time cost tracking for AI coding agents with budget limits, kill switch, and TUI dashboard.

Markdown kanban board for AI agents and Claude Code

PM-driven review-loop orchestrator for AI coding agents

MCP server providing persistent notes, todos, timers, and a cross-project registry — capabilities that augment Claude Code's built-in harness.

Good tools for pretrained language models as agent developed by zhwang.

CLI tool for tracing AI-generated code changes

MCP server that diagnoses why your agent behaved the way it did, and how to fix it

Record, replay, and debug AI agent execution traces

.track — lightweight ticketing & agent coordination for multi-agent coding workflows

Replay and diff AI agent event trajectories for debugging regressions. Python port of @mukundakatta/agent-trajectory-replay.

Rank multi-agent trace failures by severity. CLI + web dashboard + OTLP receiver, with optional LLM root-cause analysis.

Local Codex plugin for iterative Agent tuning with guided Skills, reusable runner templates, versioned results, and static validation.

Reference implementation for the Agent Almanac Code Uniformity benchmark

Update Claude Code sub-agents from GitHub to your project

Generate a local dashboard from Codex CLI / Claude Code / Cursor agent logs

Run coding-agent CLIs in an isolated profile and workspace.

Remote voice bridge connecting phone browsers to Claude Code