Code agents

Let your LLMs call each other — a local MCP switchboard for coding agents

Text-interface LLM control plane for semcod/coru shell automation (pair with gillm for GUI).

LangChain retriever for trelix code intelligence

LlamaIndex retriever for trelix code intelligence

Tsugite plugin: Claude Code provider (routes LLM calls through the claude CLI)

Deterministic local runtime governance kernel for autonomous coding agents.

A clean-room terminal agentic coding assistant with BYOK model providers, sandboxed tools, sessions, skills, hooks, MCP, and multi-agent extension points.

Zolvix local file agent — connects your codebase to Zolvix AI

Autonomous AI agent orchestrator — Claude, GPT, Codex, and local models (Ollama/LMStudio/llama.cpp)

mycel — AI agent orchestration. Coordinate teams of Claude, Gemini, Cursor, and other AI agents.

AI agent orchestration framework for OpenCode — PRD to engineering docs pipeline

Universal Security Verification Framework for AI Agent Installations

Trusted dependency manager for AI agent skills

A Senior Business Analyst AI agent - analyses websites & requirement docs, outputs a professional requirements.md

Detect whether a JavaScript CLI is running inside a coding agent.

ZevaiRouter - AI Router with provider automation, multi-account workflows, and quota tracking

Unify Claude Code, Codex, Cursor, and Gemini CLI with persistent context, governance, and multi-model debate.

Global CLI: freeclaude — Claude Code opened to any LLM (OpenAI, Gemini, DeepSeek, Ollama, etc.)

Promptbook: Create persistent AI agents that turn your company's scattered knowledge into action

OMO-flavored terminal coding-agent harness with real LLM calls, approved shell execution, and durable session ledgers. Inspired by Gajae-Code, built on oh-my-openagent philosophy.

Personal experimental fork of opencode-ultra with AGORA debate keyword and Fusion-Fable Mode (FFM) orchestration. Research and personal use only.

The OpenCode harness connects `HarnessAgent` to OpenCode through a sandboxed bridge.

OmniLearn — AI-powered adaptive learning workflow for OpenCode. Multi-agent orchestration that creates personalized roadmaps, hands-on assignments, and tracks progress across any skill.

Multi-agent swarm coordination for OpenCode with learning capabilities, cells integration, and Agent Mail

Spec-Driven Agent Framework - Desenvolvimento orientado por especificações para agentes LLM

LangGraph-powered autonomous CLI agent with guarded execution, local RAG, and memory-scoped planning.

Pragmatic, Gemini-powered AST Call-Graph AI Code Reviewer CLI

Portable handover bundles for coding agents.

AgentGuard — AI Code Security Scanner + Auto-Fixer

Offline cross-machine sync for Claude Code sessions (JSONL) and memory (.md).

Lint your Claude Code skills: descriptions that never trigger, silent frontmatter typos, boot-token cost.

Control an existing interactive Claude Code session from Telegram.

Production-grade RAG + multi-LLM framework — hybrid search, streaming, cross-encoder reranking, and a REST API

Run coding agents and only mark work done when independent checks pass.

An autonomous, multi-turn AI debugging agent built from scratch using AST surgery.

Reeflex Claude Code adapter: deterministic PreToolUse governance hook (allow/deny/require_approval), fail-closed by construction.

Local auth-code challenge plugin for uv-agent.

Guardrail checks for AI-agent-generated pull requests

AI agent team installer — 20 specialized personas for product development

Zero-dependency TypeScript SDK for the fastsearch REST API — hybrid search over docparse chunks, with first-class helpers for LLM agent development (tool definitions, RAG context, retrievers).

true402 tools for LangChain — pay-per-call on-chain rug/honeypot & address safety plus backlink/keyword SEO data for Base AI agents over x402 (USDC, no account, no API key).

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

ZypeCode — A terminal-native coding assistant powered by free AI APIs

hara — a coding agent CLI that runs like an engineering org.

Correlate AI coding agent token usage with git output to measure ROI

Local-first financial accountability CLI: Claude Code/Codex attribution, provenance, and next actions, plus experimental Gemini CLI cost evidence.

Report how much rate limit or subscription quota each registered Smithers account has consumed, across Claude, Codex, OpenAI, Anthropic, and Google providers.

Fine-tune cheap open-source LLMs (GLM, Qwen, DeepSeek) on your AI coding agent's successful runs with LoRA (SFT + DPO) so your model cascade escalates to expensive frontier models (GPT, Claude) less often — cutting cost-per-resolved. Turns run history int

領域無關的 agent 底座（kernel + 可插拔 DomainPack），從 xitto-code 抽象而來

终端优先的 AI 编程 Agent，用自然语言在本地仓库中读代码、改代码、跑命令、调试问题。

An AI coding agent that writes code for you. Run it from your project directory, tell it what to do, and it reads and writes files, runs commands, and iterates until the task is done. Supports sub-agents, custom tools, and Bring-Your-Own-Key providers.

Loop-core multi-agent coding tool — plan, delegate, review, repeat.

A multi-agent AI framework for building software with professional quality, across Antigravity, Claude Code, Cursor, Codex CLI, OpenCode, GitHub Copilot, Windsurf, Cline, Roo Code, and Zed.

OpenCode provider for the Nonoka Agent framework

Installs the Android Agentic Dev Loop (Gate/Analyse/Design/Implement/Evaluate) into an existing Android repo in one command.

Shared Agentic Loop Working domain models and registry loading utilities.

Parallel agentic planning and test-time compute scaling for pi coding agents.

Always-on containerized dev environment for AI coding agents, driven over SSH+tmux.

agent-hotwash — analyze coding-agent traces to surface improvement opportunities and bad patterns

Map every AI API call in a codebase — offline, no LLM, no keys. Opens a webpage of your providers, models, and agents.

Manually switch between multiple Claude Code accounts by swapping local credentials.

AI-powered git diff analysis and code review with RAG context

The Mandate Agent SDK — Trust Engine for the Agent Economy

Telemetry engine for DevFlow — record and analyze AI agent execution traces.

Vertex AI Agent Engine deployment inspector and runtime validator

SDK and CLI for SkillDB — discover, install, and manage AI agent skills

Browser automation CLI for web scraping, headless browsing, SEO analysis, and AI agent workflows. A command-line alternative to Playwright, Puppeteer, and Selenium.

OpenCode plugin — define custom AI agent roles via YAML with per-role prompts, models, skills, and permissions

Move your AI agent sessions between Claude Code, Codex, and OpenCode

Headless, configurable in-browser LLM agent on the Vercel AI SDK: multi-provider bring-your-own-key (OpenAI, Anthropic, Google, xAI, DeepSeek, gateway, openai-compatible) AND local WebGPU/WebLLM, native + prompted tool-calling, structured output, an encry

React bindings for @dudko.dev/agent-web: a headless useAgent hook, an AgentProvider context, and optional pre-styled components (chat panel, plan/step view, BYOK key form, WebLLM load bar) that connect the in-browser LLM agent to any React site. UI you ca

CSS intelligence for AI coding agents — surgical style context, fewer tool calls, faster answers. 100% local.

Общие модули для TypeScript агентов в agent-toolkit

Excalidraw toolkit for AI coding agents — agent skill, CLI, and MCP server with a live canvas

Local Claude Code Router gateway with CLI and web management UI.

Pi extension for monitoring Z.ai, DeepSeek, OpenAI Codex, and Opencode Go usage

Universal installer and agent pack for the m1nd MCP runtime.

A model-agnostic CLI coding agent for the terminal — any provider, local or cloud, with plan/execute/yolo modes, subagent orchestration, and long-term memory.

Run local coding agents in a cross-audit loop on any git repo — author, cross-audit, test-gate, merge. Educational; not for production.

Deterministic, config-driven multi-agent delivery pipeline (client -> orchestrator -> workers). Zero runtime dependencies.

The programmatic **SDK** for AgentPrism — run dynamic, multi-agent **workflow scripts** (`agent()` / `parallel()` / `pipeline()` / …) over real coding-agent backends through the [Agent Client Protocol](https://agentclientprotocol.com) (ACP).

8-phase AI development pipeline with full orchestration on Claude Code, Copilot CLI and Codex CLI. Analysis, planning, TDD, CLI-aware parallel review with consensus surfacing + Fable triage, default-FAIL evidence gates, secret + intent guards, per-phase c

A private reasoner for your terminal. Direct conversation or grounded multi-agent research, GPU-native and fully local. No API keys, no inference servers.

Autonomous Pentest Platform - AI-Driven Security Testing with Multi-Agent Orchestration, Scope Enforcement, and Automated Finding Reports

CLI tool for AgentQuilt agent framework — compiles Markdown fragments into deployment-ready agent instructions with deterministic versioning

Kaboom Agentic Browser is an AI debugger, inspector, and verification toolkit for local-first browser development workflows.

ACAIAgent — a model-agnostic layer for the Claude Agent SDK. Switch models mid-session without losing context. Bring your own models.

AI Agent 客制化配置中心 — 统一管理多 Agent 配置，一键启动

A LangGraph + Ollama coding agent usable as a library via agent.run(query)

A tiny CLI for delegating bounded agent tasks across coding-agent runtimes.

LangChain chat model provider for Apple's on-device Foundation Models framework

OTel-native MeshAI connector for Claude Code: durable, evidence-grade telemetry for AI coding agent activity

Generate MCP servers from plain-English skill descriptions

General-purpose coding agent — Rust TUI/CLI + Python gateway runtime

Cobalt acts as your personal AI developer by taking on coding tasks directly in your GitHub repository. It handles the setup, testing, and running of your app s

Laravel/PHP AI agent skill — compatible with Claude Code, Cursor, Windsurf

Scaffolds and orchestrates AI-agent development workspaces.

HarmonyOS programming development AI agent

AutoWonder local runtime — execute AI agent dispatch packages on your machine

The Best AI Agent Harness for Chinese Enterprise - OpenCode Plugin with Multi-Agent Orchestration, 20 Skills, and Background Task Management