#coding-agent

The local merge queue for parallel Claude Code agents

解决DSH 官方尚无终端 TUI 痛点的补位之作，献给偏爱cli的各位极客：Claude Code 风格全屏交互终端插件——像素鲸鱼顶栏、实时工作状态行、思考流式展开、双击 Esc 回滚、上下文进度条 + TPS 仪表。npm 一键安装。

A programmable tool and agent runtime for Pi

Stop your coding agent reading the wrong files. Compiler-grade TS/JS repo map — 100% precision on blast radius vs grep's 60%, measured on public repos. CLI + MCP server, fully local, no vector DB.

Auto-updated leaderboard of trending claude-skills and AI agent repos, refreshed every 15 minutes

Oh My Tianshu 是一款完全体开源 coding agent:在 dsh harness 基础之上带视觉、跨会话记忆、验证门、agent 路由、语义 + 图谱代码检索、文件回滚和全屏终端 UI——全部以插件组合。它是 DeepSeek Harness(dsh)的友好 MIT fork,保留上游一切皆插件的架构,界面交互对标 oh-my-pi。

Interactive terminal coding agent in Rust — runs the DeepSeek V4 Flash model locally on macOS (Metal), with a Ratatui TUI, a full tool suite, MCP, and persistent sessions.

Python implementation of coding agent core mechanisms, with architecture comparison across Claude Code / Kimi Code / Codex

Self-hosted mission control for real Claude Code and Codex sessions — persistent terminals, automations, and browser/mobile control.

A fully featured WebUI development environment for the Pi Coding Agent.

Not just an agent demo — a local coding-agent platform: plan mode, sub-agent teams, cron, memory, MCP. Single Go binary, DeepSeek-native, MIT.

The best Pi coding agent setup — 10 packages, 59 skills, 10-step autonomous workflow. Zero bloat, zero MCP, pure Pi ideology.

Ephemeral local dev environments for coding agents — works whether your stack lives in Docker, on the host, or a mix. Run agents in parallel; each worktree gets isolated ports and data. No collisions, clean teardown.

NordRelay is a secure remote control bridge for coding agents, connecting Codex, Pi, Hermes, OpenClaw and Claude Code to Telegram, Discord, Slack, WebUI with streaming replies, sessions, files, voice, queues, artifacts and access controls.

基于 DeepSeek 大语言模型的 AI 编程助手 Agent —— 自然语言驱动的终端编码助手。支持自动读写文件、代码搜索、命令执行、Git 管理，复杂任务智能拆解与多 Agent 并行执行。

An agent runtime and extension platform in pure Python — self-hosted, auditable, and extensible on the model budgets you already pay for.

Awesome Claude Code And Agent Tools

CLI coding agent สไตล์ Claude Code — Claude API / Cloud / Ollama / llama.cpp, 42 skills, single-file

Control Claude Code in VS Code from Telegram: read sessions, answer questions, approve or deny commands, and keep coding agents moving from your phone.

Sleek, fast, token-efficient AI coding agent. Multi-provider (Cortex, OpenAI, Anthropic, Ollama) with a polished terminal UI. Fork of vix.

一个简单好用的 context 分层管理工具：遵循 CoALA 认知架构，兼容 Matt Pocock skills，配合工程执行 skill 使用，1+1>2

Rel.AI MCP - a local coding agent for ChatGPT Web. Let ChatGPT read and edit repositories, run commands and tests, review changes, and use Git through MCP.

A quantum prompt playground & macOS-native Rust coding agent: morphing fluid entropy into rigid execution checkpoints. Entropy cannot lie.

MiMo 模型的原创开源终端 AI 编程 agent · 像 Claude Code / Codex CLI 一样在终端跑 · MIT 开源不收费

Self-hosted AI coding agent control plane for Claude Code, Codex & Cursor: tmux browser terminals, remote clients, searchable agent history, git worktrees, and OpenAI-compatible summaries.

Launch any AI coding-agent CLI — Claude Code, Codex, GitHub Copilot, Cursor, Crush, OpenCode and more — from one VS Code sidebar. Works in VS Code, Cursor, Antigravity & Windsurf on Windows, macOS & Linux.

Community GitHub Action for DeepSeek Harness — AI Code Review · CI Diagnosis · Auto Fix · Issue → PR

Provider-independent coding agent for your terminal — fast Rust TUI + headless mode, OS-sandboxed, multi-provider

Live index of Claude Code extensions, hooks, and plugins — refreshed every 15 minutes from GitHub

Audits what your Claude Code agent did against what it said — reads session logs and git, cites evidence, calls no model

Delegate bounded coding tasks from Codex or Claude Code to local Ollama models.

🏭 Coding agent CLI engineered to make any LLM — local or cloud, frontier or 7B — actually useful. 16 providers, multi-tab sessions, automatic key+model failover, plan-mode review, MCP, and recovery loops for models that misbehave.

Claude Opus 4.7 native Plan-Execute-Verify coding harness — a Claude Code plugin that enforces a 3-phase pipeline with hook-driven verification

Work while you sleep — a host-native autonomous coding agent that lands draft PRs by morning.

PAPPO is a patch-aware reinforcement learning algorithm and experimental RL framework for tool-using coding agents. It provides turn-level credit assignment, PPO training utilities, rollout extraction, critic baselines, benchmark runners, and reproducible evaluation pipelines for repository repair tasks.

欲しい機能を言うと、アプリが自分で作る。ただし暴走はしない。安全な自己進化型デスクトップAIエージェント / Self-evolving desktop AI agent with safety gates

Provider-agnostic coding-agent harness + DeepEval evaluation suite

Agent EcoRadar — always-on radar that scans, scores, and indexes the AI coding agent ecosystem

Let your coding agent drive the other AIs on your machine.

Nokori (残り) — behavioral memory layer for Claude Code and Cursor. Turns your corrections into rules that come back when it counts. 经验留下的痕迹，比记忆更深。