Code agents

A local-first task, evidence, and independent-review layer for AI coding runtimes

Local-first safety scanner and incident report generator for AI coding agent workspaces.

Hierarchical SystemRDL 2.0 authoring reference for coding agents, packaged as an agent skill.

MCP plugin that gives opencode agents tools for visual interaction (HTML forms, dashboards) with users

面向学习者的 AI Agent 执行调试器

Production-grade agentic code reviewer: multi-step LLM workflow with context retrieval, verification, and reproducible benchmarking.

Stops your coding agent from pushing unverified work. Your agent does the reviewing; a state machine records the result per-commit and gates the push.

Coding Agent domain runtime built on AIHI Agent

CLI RAG tool for local codebases

Convert ChatGPT web conversations into aidialog dialogs

Convert ChatGPT web conversations into aidialog dialogs

Universal bootstrap framework for Claude Code projects

Local-first cost observability for Claude Code sessions

通过openai兼容的api代理运行claude code, 不修改claude code的配置

The workspace layer for Claude Code - persistent project memory, an interactive architecture graph, MCP awareness, and per-project launch control in a fast terminal UI

Hop Claude Code between several Claude accounts without logging in again — swap the saved OAuth login in one keystroke, keep every account's usage pool separate.

A virtual co-worker that picks up Jira and Azure DevOps tasks and solves them with coding agents.

AI-powered documentation generator for Python projects

The /fastbuild agent: drives coding agents through a FastBuild task graph with AST-backed project memory.

HexaLLM — AI coding assistant for the terminal

Reusable Jira → Claude Code → Spec-Kit specification toolkit

Zero-dependency LLM call tracer — patch once, trace everything

A local, private anthology of every AI coding session — browse, search, spawn-tree, faithfully export and safely manage ChatGPT / Claude / Gemini / Codex history. No network, no egress.

Share an LLM API quota across devices on a local network (Wi-Fi hotspot, USB tether, or LAN)

Local hybrid retrieval (BM25 + embeddings + RRF) for agent memory and codebases — one SQLite file, MCP server included.

Per-app developer agent for applications generated by Naviscom Shipyard.

Canonical delegation contract schema + enforcement hooks for parent->subagent fidelity in AI coding workflows.

A local coding and terminal AI agent powered by an OpenAI-compatible Llama server.

A code agent built from scratch, no frameworks

Python SDK that enables developers to build and deploy Claude Agent SDK agents to the UiPath Cloud Platform

Monitor, debug, and optimize your AI agents. Track LLM calls, costs, latency, and tool usage in real-time.

AumOS Agent SDK — unified Python SDK that gives coding agents AumOS security primitives as first-class objects

Snipara gives coding agents a shared view of project decisions, risks, impact, proof, and next steps. It helps agents start with the right context instead of gu

Adds a company-policy check before consequential AI agent actions run.

Porcupine — a terminal AI agent that plans, acts inside explicit permission modes, and verifies its work. The whole Porcupine codebase ships as one package.

Local CLI for finding and resuming AI agent sessions across local projects.

Run your own AI agent as a ProhostAI teammate, and stream your account's webhooks to your laptop.

脑珊瑚 Coral Memory — 面向 LLM Agent 的热度感知记忆层（DeepSeek Harness 插件）：MCP 记忆工具（memory_search/insert/thread_* 等 16 个）+ 设置面板（统计/容量/检索/配额）。作者：Mr. Code Muggle (@Ne)。

Spec-driven development for LLM coding agents: 9 skills + a stdlib evidence engine. Facts block, guesses advise; the human approves.

See exactly what your AI agent did. Lightweight tracing + a local dashboard for debugging LangChain agent runs.

OpenAI-compatible HTTP server over ACP agents. Use Claude Code, Codex, opencode or any ACP CLI from anything that speaks the OpenAI API but does not speak ACP yet.

Agent-plane presentation selector: composes one agent's tools as Code Mode, native, or both

ACP adapter for pi coding agent

Local-first, single-user general agent for the command line.

Local x402-paying proxy + MCP server for openzoo.fun — point any OpenAI-compatible harness (Cursor, Claude Code, aider, SDKs) at localhost and it pays per call from a local burner wallet. Solana and Base rails live; Robinhood experimental.

Codex CLI-backed agent adapter for alint

Open-source schemas + loaders for the three guuey config files: agent.json (declarative agent definition), guuey.json (hosted-deploy overlay), and the helper types around them. Consumed by @guuey/cli, the guuey backend, and devs writing their own agent or

Minimal Pi extension for OpenAI Fast mode.

Turn one approved plan into a team of AI coding agents that build it in parallel, in isolated git worktrees, from inside your editor.

EU-hosted AI coding agent with Ink TUI, tool execution, skills, slash commands, and plugins. Mistral La Plateforme by default. Your code stays in Europe.

通过 Web 操作本地 Coding Agent 的应用

MCP server for summon-agents: dispatch an approved plan to parallel AI coding agents from Claude Code, Cursor, or VS Code.

Headless library for building control loops: scheduled bots that scan a repo for a class of anomaly, fix a few instances with a coding agent, and open a PR — no server, UI, or persistent process.

A requirements-led, task-driven workbench for secure autonomous Agent delivery

ANTRI Code - The Autonomous Agentic CLI & Desktop Assistant

Autonomous AI coding agent — explores your codebase, diagnoses root causes, writes fixes, and runs tests. Supports Claude, Gemini, DeepSeek, and Kimi K2.

Autonomous AI coding agent CLI powered by 9router with full Antigravity experience

macOS voice capture, transcription, text-to-speech, and autonomous narration for Pi agents.

Rendobar SDK: TypeScript client for the media processing and AI generation API.

An open source low-code development platform

Smart dev server launcher: error→AI search, success→auto-open browser. Any CLI tool.

AgentTeams for DeepSeek Harness: multi-agent team collaboration (captain, members, tasks with dependencies, messaging) driven by natural language, with a tree monitor in the web GUI

TGO — a thin multi-agent orchestration plugin for OpenCode

Multi-agent workflows with full observability and time travel: watch every step live, rewind, fork, and replay any run. Claude Code, Codex, Gemini, Hermes, OpenClaw, any model or harness.

Multi-agent development workflow for OpenCode, with V3 profiles and an executable workflow engine

Pi extension for single-agent delegation and scripted multi-agent workflows

Project-local Codex multi-agent workflow for Tantu Wuyou frontend projects.

Autonomous AI multi-agent coding CLI: describe the work, get back a git branch

Multi-Agent Development Skill with a model-neutral Python Runtime template

AI-first sandboxed agentic development workbench — task orchestration, hierarchical memory, sandbox mediation, multi-agent parity, pluggable deployment.

Parent-workspace AI development harness for multi-repo, multi-agent engineering work.

Deterministic, resumable multi-agent workflows — a harness-agnostic MCP server that orchestrates Codex, Claude, Cursor, and Kimi agents from plain JavaScript, with journaled resume, git worktree isolation, and personas.

Zelari Code core library — provider-neutral agent loop (AgentHarness), multi-agent council orchestration, and built-in skills. Used by the zelari-code CLI; consumable by other agent frontends.

kixparadigm-en — English edition of the kix paradigm preset for DeepSeek Harness: resident cognition layer (EN) + kixpower multi-agent orchestration, one-command import (preset + vision-bridge + guard plugins)

Multi-agent, multi-provider harness for building software autonomously with any LLM. Researcher, Planner, Curator, Generator, Evaluator, Documenter pipeline with a fail-closed security-audit gate, a fleet orchestrator for bulk multi-agent runs, and a cros

Standalone, multi-provider AI Agent framework in plain JavaScript

Hono server and file-system loader for the bread agent framework (importable library).

A local-first, zero-dependency Spec-Driven Agentic Workflow Harness for coding agents.

Web GUI for agentic dev workspaces

Minimal harness for agentic coding and more.

Agentic code analysis CLI for model-backed lint rules

The forecasting intelligence platform for agentic traders.

Provider-neutral program planning and agentic delivery pipeline

Diff call stacks across git commits for agentic code review (22 languages)

A CLI for OpenRouter with Agentic capabilities - AI coding assistant

MyPi agentic coding CLI with an isolated, customized Pi runtime

GUPPI — General-purpose Unifying Pluggable Intelligence & Agentic Sidecar

QA Agentic Workflows for OpenCode — 9router edition

W1, the agentic work surface for your terminal.

Seal outcomes, verification, and decisions into an auditable workflow for agentic coding

Coda CLI — agentic coding assistant (native binary launcher)

agent — the pi coding agent with the Constructive harness baked in, purely a shell

Version-aligned codex agentic tool integration for Agor

Zeus — an agentic coding CLI for the terminal.

Version-aligned opencode agentic tool integration for Agor

Mirai agentic coding CLI with Ink UI, slash suggestions, and subagent sessions

Spec-first and quality-gated skills for agentic software development

Official Model Context Protocol (MCP) server & SDK for XentFi — give AI agents (Claude, Cursor, ChatGPT, ElizaOS, CrewAI, Codex, VS Code...) secure, policy-governed wallets, payments, and treasury tools.

A2A Protocol v1.0 bidirectional extension for the Pi coding agent — distribute tasks to remote agents, be called by them, and self-declare for local session discovery.

Multi-agent orchestration CLI — dispatch coding agents (Codex, Claude, Aider, etc.) in parallel