Code agents

Agentic RAG over any PDF — grounded, cited answers from research reports, ESG/sustainability disclosures, contracts, manuals, and filings. Multi-agent LangGraph workflow with hybrid retrieval, RAPTOR summaries, NL→SQL over extracted tables, CRAG corrective loops, and a defense-in-depth hallucination stack.

An agentic scriptorium for scholarly writing — coordinated AI capabilities for manuscripts, grants, and reviews.

Python bindings for the Agentic C++ SDK — orchestrate coding agents and LLMs with a unified session model, event stream, and tool system.

code for an agentic search tool using Langchain

Agent-driven software engineering framework — transforms work tickets into code, tests, docs, and deployments through specialized LLM agents.

Agentic Coding Standard CLI - Scaffold .agent/ directories for AI-ready codebases

Model Context Protocol (MCP) Server for AI Data Privacy: LLM prompt firewall, audit logs, and 31 MCP tools for Claude, Cursor, and Windsurf.

Orchestrate teams of AI coding agents in tmux

Agentic Testari — autonomous QA testing under AIOS development discipline

A TUI primitive for coding agents — streaming markdown, tool calls, diffs, and more in linear scrollback with zero flicker.

Claude Code runner and orchestrator — thin job lifecycle, repo management, and OTEL pipeline

Instant codebase map for AI agents — understand any project before making changes

A unified, scalable, production-ready multi-agent application development framework

Cryptographic identity for AI agents. Verifiable Ed25519 tokens replacing hardcoded API keys.

Python Toolkit for Declarative AI Agent Development

Hook system and MCP tool server for Claude Code agents

A comprehensive toolkit for AI agent development and workflow orchestration with Gemini AI integration

AI Agent Observability — trace, monitor & debug your AI agents in real-time

AgentJoy Bridge CLI (Codex / Claude Code / Agent tool activity -> AgentJoy Runs)

Multi-LLM Council Backend for AGENT-K - Three-stage consensus with GPT, Gemini, and Claude

Official Python SDK for the agentkata.dev solver platform

A unified search and knowledge tool for AI agents and developers

Python SDK for agentkernel — run AI coding agents in secure, isolated microVMs

Cross-platform CLI for switching Claude and Codex API profiles.

Unified CLI for the Agent Quality Toolkit (agentmd, coderace, agentlint, agentreflect)

Developer SDK for building personalized voice AI assistants

A developer library for LLM-based agents

Main package for developing agents and experiments

Devtool to document and inspect LLM agent systems.

Law-first governance kit for AI coding agents: installable scaffold + memory MCP server that lets agents read project rules before they write code.

Python agent for coding and research

MCP server for AgentLens — zero-code observability for MCP-native AI agents

LLM observability, quality scoring, hallucination detection, cost tracking, agent run debugging, and drop-in LangChain + LlamaIndex callbacks — in 2 lines of code.

Debug AI agents visually — self-hosted, open-source observability SDK

Python SDK for AgentLens — observability for AI agents

The interactive debugger for LLM agents. Pause, inspect, and fork any agent mid-run.

Track and debug AI agents step-by-step

Local-first AI agent debugger with fork & replay

See what your agents think. Open-source AI Agent observability platform.

Framework for development and execution of agents for control and simulation of energy systems.

Framework for development and execution of agents for control and simulation of energy systems.

Real-time quality guardrails for AI coding agents

Lint, score, and optimize AI agent configuration files (CLAUDE.md, AGENTS.md, Cursor rules)

Persistent decision memory for any project. Karpathy's LLM Wiki, productized.

Simple, colorful debug logs and logfiles.

AI application development framework for stable structured outputs, observable actions, and durable workflows.

Observation and developer tooling companion package for Agently

Official SDK for developing extensions for the Agently framework

Agently Stage - Efficient Convenient Asynchronous and Multithreaded Programming

AgentMake AI: an agent developement kit (ADK) for developing agentic AI applications that support 16 AI backends and work with 7 agentic components, such as tools and agents. (Developer: Eliran Wong)

WebUI for AgentMake AI; AgentMake AI: a software developement kit for developing agentic AI applications that support 16 AI backends and work with 7 agentic components, such as tools and agents. (Developer: Eliran Wong)

Cryptographic provenance for AI-generated code

Analyze codebases and generate optimized context files for AI coding agents (Claude Code, Codex, Cursor, Copilot)

Local-first multi-agent coordination and provenance for coding workflows

MCP Server for Claude Desktop - Agent OS kernel primitives including code safety verification, CMVK multi-model review, and IATP trust

Agent security mesh: 27-endpoint proxy + 12 framework SDKs + coding-agent hooks, composing 54 Tessera modules with SPIRE, agentgateway, and OpenTelemetry.

Monitor your AI agents. Track cost, latency, and errors in two lines of code.

All-in-1 MCP server for developers

Canonical configuration manager for AI coding agent components

Python Library for AI/LLM Agent Development with UI-Driven Workflows

MCP server adapter for AgentNode — expose AgentNode packs as MCP tools for OpenClaw, Claude Code, Cursor, and other MCP clients.

Developer tools for inspecting and debugging AgentOBS traces

A terminal UI tool for monitoring local AI coding agents (Claude Code, etc.)

Observability and DevTool Platform for AI Agents

AI-powered development platform: Multi-agent system for requirements discovery, conversational document building, and test automation

DevTorch — AI reasoning capture, audit trail, and governance for agent-assisted development

AgentOS is a command line interface and python developer API for building, running, and sharing flexible learning agents.

Deterministic record, replay, and git-bisect for AI agent runs. Reproduce a broken run byte-for-byte offline, then binary search to the commit that broke it.

A code-first agent framework for seamlessly planning and executing data analytics tasks

Local context engine for AI coding agents that ranks relevant repo files and builds compact task-focused context packs for Claude Code, Codex, Cursor, Windsurf, MCP, and CI workflows.

Multi-language code execution against a real directory for AI agents

An execution gateway for AI agents on untrusted devices

The payment protocol for AI agents. Let any AI agent send and receive crypto payments in 3 lines of code.

TUI inspector for agent CLI configuration directories like ~/.claude/.

MCP server that bridges AI coding agents to developers via AgentPing

A shared to-do list for AI agents. Dependency-aware task queue, zero dependencies, pure Python.

agents.txt for any repo. Tell autonomous AI agents what they're allowed to do, in 60 seconds.

Universal MCP server that exposes coding agents (Copilot, Claude Code, Codex) as subagents via a unified tool interface

Python MCP server for agentpromocode.com resolve + feedback tools

AI Agent Observability SDK - Auto-instrument your AI agents with one line of code

Enterprise AI Engineering Control Plane — secure, token-optimized, context-aware governance for coding agents.

Local-first visual debugger for multi-agent AI systems

Assess and bootstrap git repositories for AI-assisted development with automated remediation

Code intelligence engine for AI coding assistants

Score your codebase on how ready it is for AI agents — and coach you through the fixes.

Generate LLM-friendly code review payloads from git or sl diffs

Agentrix CLI: run coding agents headless, from anywhere.

Agentrix agent runtime: surface-agnostic, production-grade coding agent.

Quickly develop and run ABMs! Written in Rust for use in Python.

AGENTS.md/CLAUDE.md generator and ExecPlan harness for coding agents

The easiest way to run AI or user generated python code safely in a docker container

The easiest way to run AI or user generated python code safely in a docker container. This is a fork of the original AgentRun repo with additional customization options added.

AI-powered CLI tool for code editing and terminal commands (OpenRouter)

Pre-built agentd binary for running coding agents behind one API

Lightweight, hackable multi-agent orchestration lab (CLI + Python) with transcripts, checkpoints, budgets, and pluggable providers/tools.

Terminal animation effects built with braille, block characters, and unicode glyphs

MCP server that analyzes codebases and generates AGENTS.md files

The deterministic merge gate for AI-generated agent capability changes. Shows what a PR changes in coding-agent configuration (Claude Code settings, .mcp.json, hooks, Codex, Cursor, VS Code MCP, GitHub workflow permissions) with no manifest. Agent release readiness for tool-using AI agents. CLI + GitHub Action. Scans MCP, OpenAPI, OpenAI Agents SDK, Anthropic, Google ADK, LangChain, CrewAI, OpenAI API, Codex config, Codex plugin, n8n, Conductor OSS workflow JSON.

Multi-agent orchestrator skill for Claude Code

Python SDK for the AgentSandbox API - sandbox execution service for Python/Bash code