Coding agents, page 3

Orca Agent — a DeepSeek-native terminal coding agent

513 stars+1 this week

A small, powerful, open-source CLI coding agent that works with open models.

357 stars+4 this week

Local-first MCP plugin for continuous software-quality review by AI coding agents, powered by Jev.

249 stars+2 this week

A scrolling terminal multiplexer that tracks your AI coding agents.

137 stars0 this week

Save up to 30% of your AI coding tokens. Scubiee turns any codebase into searchable context for your AI coding agent. A local context engine for Cursor, Claude Code, Copilot, Codex, and more: semantic search, code relationships, live sync, MCP integration, and code that never leaves your machine.

146 stars+1 this week

Give a coding agent a brief, not a chat, and it works on its own across sessions. Includes an example run: an open-world city built in a real game engine with no human help. In early development.

400 stars0 this week

MathCode: A Frontier Mathematical Coding Agent

751 stars0 this week

Agentic coding TypeScript boilerplate for Claude Code: sub-agent workflows with built-in quality checks and context engineering.

236 stars0 this week

Open-source desktop and web coding agent with a first-party host and harness, durable sessions, model connections, streaming chat, and workspace tools.

120 stars0 this week

Turn AI coding into an engineering process.

228 stars0 this week

My Pi coding agent setup: secret redaction, LSP, searchable context, recall, telemetry, observability, and team mode. Toggle with /extensions.

139 stars+1 this week

Cross-model review skills for Claude Code and Codex CLI: one agent orchestrates, another model reviews plans, code and reasoning.

167 stars+7 this week

Cheaper and better Greptile alternative runs on your own github actions.

100 stars-2 this week

Coordinate multiple AI coding agents through a local-first, recoverable Agent Bus.

106 stars0 this week

You write the specs. It clears the board: coding agent chains plan, review, implement, verify and merge unattended on your own machine, on the GPT and Claude subscriptions you already have.

195 stars+3 this week

A keyboard-first menubar app to monitor and jump between AI coding sessions — minimum setup required.

161 stars0 this week

All-in-one terminal workspace for desktops and servers: editor with LSP, file manager with SFTP/FTP, terminal, git, database viewer and a coding agent in one zero-config static Rust binary.

185 stars+2 this week

Unified CLI for running AI coding agents in isolated containers. Includes built-in local metrics collection, HTTP traffic tracking, and an analytics dashboard to track agent actions.

190 stars+1 this week

Open-source desktop app for a local coding agent. Watch every tool call, diff, and terminal command. Bring your own models; sessions stay on your machine.

217 stars+2 this week

Gives developers and coding agents one reliable edit loop

332 stars0 this week

Your coding agent starts every session blank. Rekal is the memory your team is missing

206 stars+1 this week

Reusable project context and specialist workflows for the AI tools you already use. Agents, skills, rules and MCP tools for Claude Code, Codex, Copilot, Cursor and more, plus SDLC workflows, session memory, and Jev decision support that offloads bounded LLM decisions to save tokens.

229 stars+2 this week

Shared context, memory, and task coordination across AI coding agents. Single Go binary, local SQLite, hybrid keyword and semantic search.

297 stars-2 this week

Claude Code, Codex, and multi-agent configuration system: principles, hooks, skills, and workflow patterns for AI-assisted development

214 stars+1 this week

A free coding agent in your terminal. It runs on the smartest free model that is up today.

6,562 stars+6 this week

Persistent memory and skill framework for Claude Code: session diary, fact recall, 87 free skills, MCP skill loader

430 stars+3 this week

An AI coding workstation that fits in your pocket.

110 stars0 this week

💃 Dance with Intelligence in Your Code. Minuet offers code completion as-you-type from popular LLMs including OpenAI, Gemini, Claude, Ollama, Llama.cpp, Codestral, and more.

1,451 stars+11 this week

A set of pi-extensions, including pi-continuous-learning that continually improves you pi coding agent experience

155 stars-1 this week

One window for all your AI coding agents. Run Claude, Codex, OpenCode, Gemini, Antigravity, Cursor, and Copilot side-by-side. Terminal and chat, any layout.

121 stars0 this week

CodeEvolve is an open-source evolutionary coding agent for algorithm discovery and optimization.

155 stars+2 this week

为 DeepSeek 前缀缓存定制的终端 Code Agent(纯 Go),缓存命中率 95-99%,命中输入定价为未命中的 1/30。A terminal coding agent optimized for DeepSeek prefix caching — 95-99% cache hit, cache-hit input priced at 1/30th of cache-miss.

138 stars+2 this week

Project management skill system for Agents that uses GitHub Issues and Git worktrees for parallel agent execution.

8,438 stars+14 this week

Stop hooks that stop AI coding agents (Claude Code, Codex) from claiming "done" without proof. A Lean quality system: every defect becomes a permanent countermeasure. Built by a manufacturing operator.

168 stars0 this week

Compounding Context for AI Coding Assistants — MCP graph engine for Claude Code, Cursor, Copilot, Gemini, OpenCode

1,047 stars+2 this week

A mobile vibe-coding cockpit — built on tmux: drive your live session, Claude Code / Codex — anything a terminal can run — from your phone. 移动 Vibe Coding 驾驶舱 —— 基于 tmux 实现，可在手机上驱动你的会话、Claude Code / Codex、任何终端能实现的东西。

168 stars+1 this week

An open-source, local-first AI teammate and agent operating environment for turning intent into completed work—with tools, memory, permissions, and human oversight.

147 stars+1 this week

Open source, terminal-first AI coding agent with fully transparent multi-model routing. Local (Ollama, LM Studio, MLX, llama.cpp) or cloud, your keys, one TUI. No black box.

243 stars0 this week

Solo Agent — an open-source, local-first workspace where humans and AI coding agents collaborate through channels, tasks, teams, and persistent memory.

601 stars+1 this week

UmaDev: A coding agent that works like a real dev team, commanding the Claude Code / Codex / OpenCode you already use.

266 stars0 this week

One desktop for all your AI coding Agent — Claude Code, Codex CLI & Gemini CLI. Auto-detect, one-click install, unified chat, file explorer, terminal & editor. Local-first. Built with Tauri + Rust + Vue 3.

220 stars0 this week

Multi-agent AI coding factory for one person — Claude Code PM + Codex/Qwen/Grok/Kimi/AGY writers, durable conveyor, auto-merge to main

125 stars+1 this week

Linked-Intent Development - a SDD methodology for agentic coding

118 stars+3 this week

Find, search, and resume local AI coding-agent sessions across Muse Code, Claude Code, Codex, Antigravity, Grok, Kimi, Qwen, Gemini, Cursor, and more.

163 stars+2 this week

CTX Fit finds the cheapest AI coding setup that reliably works on your repository, then applies the winner as a reviewable change.

589 stars0 this week

Engineering discipline for AI coding agents: question the request, verify against current docs, plan, build test-first on the cheapest capable model, review with a second model family, prove it before saying done. One repo for Claude Code, Codex, Antigravity, Cursor, Gemini CLI and OpenCode.

119 stars+3 this week

Find issues worth your attention.

493 stars-2 this week

GitHub Action that reviews pull request diffs with an LLM and posts the comments on the PR

372 stars0 this week

Frontend AI coding agent platform with CLI, VS Code extension, desktop app, MCP server, RAG planning, Skills, SDD guardrails, browser automation, and LoRA planner models | 面向前端工程的 AI Agent 平台，支持 CLI、VS Code 插件、桌面端、MCP 服务、RAG、Skills、SDD、浏览器自动化与 LoRA 规划模型

124 stars+4 this week

Open-source TypeScript terminal coding agent for DeepSeek-V4 — builds on DeepSeek's strong price-performance and ultra-cheap cache pricing, engineering byte-stable prefixes and cache-reusing forks so cross-session memory and a continuous self-correction layer add almost no token cost; 1M context, Skills/MCP/Hooks, Claude Code config compatible.

786 stars-1 this week

AI-powered CLI coding agent with 20+ built-in tools, MCP support, and multi-model providers

181 stars+1 this week

The most expensive bug in AI-assisted building is shipping the wrong thing, well. A drop-in CLAUDE.md / AGENTS.md for PM + eng teams using Claude Code, Cursor, or Codex: 7 principles for problem framing, scope, tradeoffs, and outcome measurement. Built on @karpathy's observations.

171 stars-4 this week

See what every AI coding agent on your machine is doing, and whether the API behind it is the one you paid for. Claude Code, Codex, Cursor, Gemini CLI and more: one endpoint for 44 model vendors, A–F API authenticity grading, per-agent permissions, usage and prompt records.

648 stars+2 this week

Open-source Agentic Development Environment (ADE) for Codex, Claude Code and other agents. Run on your own Windows, macOS or Linux machines; steer sessions, review changes and test apps from any browser.

116 stars0 this week

Open-source Claude Code plugins for multi-agent software delivery. Plan-first SDLC workflow, code review, LLM quality judges, and self-learning — grounded in your codebase. Bootstrap, Plan, & Ship.

124 stars+2 this week

A local coding harness for Mac. Chat with coding agents across cloud and local models, watch every tool call in a live activity feed, and drive a real terminal — in one window. Free and MIT licensed.

116 stars0 this week

Spec-driven, agentic workflow framework for AI coding agents. Turn a request into a verifiable goal loop — plan, act, verify — with durable specs and evidence in your repo. Works with Claude Code, Codex, Gemini, OpenCode, and plain CLI.

390 stars0 this week

Open-source agent-native visual production workspace where humans and coding agents edit the same live canvas — local-first, BYOK image/video models.

145 stars+2 this week

AI coding agent harness. Five modes: practice to playoffs. Stop your AI from over-engineering. Code like a man. Elbow out bloat. Score clean. ... AI 代理调度框架。五种模式：训练到季后赛。 别让你的 AI 过度设计一切。像个man一样，肘开冗余，干净得分。

360 stars0 this week

A model-driven harness for AI coding agents: semantic modeling, app generation, progressive API Assist and evidence-based verification.

2,819 stars+2 this week

🍣 TunaCode AI CLI coding agent with safe git branches, rich tools & multi-LLM support.

125 stars+1 this week

Agentic prompts are the most important code you're not engineering. PromptKit fixes that — composable, version-controlled prompt components (personas, protocols, formats, templates) that snap together into reliable, repeatable prompts for bug investigation, design docs, code review, security audits, and more. Works with any LLM.

114 stars+1 this week

Give coding agents a disposable Linux VM, not your laptop

1,041 stars+3 this week

AI coding agents forget. They forget across sessions, and they forget across tools. A decision you reached in Claude Code at midnight is invisible to Cursor the next morning. Honeycomb fixes that. Learn something once; recall it everywhere,

118 stars0 this week

Terminal-native AI coding agent running in containers.

233 stars0 this week

Gives a coding agent eyes and ears for any social video: timestamped frames plus a transcript, about 50x cheaper than sending the whole file to a multimodal API.

260 stars+1 this week

C# coding-agent harness (.NET 10, Microsoft Agent Framework) — sessions, tools, permissions, providers, MCP, plugins

110 stars+3 this week

The context spine that 10x's every AI coding session. Live in 8 IDEs (Claude Code, Cursor, Cline, Continue, Aider, Codex, Windsurf, Zed) via npm + OpenVSX + Anthropic plugin directory. 89% measured token reduction. Local SQLite, zero cloud, Apache 2.0.

143 stars0 this week

Loop engineering for software development. Turn any repository into a self-organizing AI engineering team — 8 specialists, contract-driven, evidence-gated, parallel feature voyages.

105 stars0 this week

The black box for AI-written code. Passive decision graph linking every commit to the agent prompts behind it: drift detection, DLP audit of what agents read, evidence-driven risk, MCP memory for coding agents, signed provenance attestations. One command, offline by default.

289 stars-5 this week

💃 Dance with LLM in Your Code. Minuet offers code completion as-you-type from popular LLMs including OpenAI, Gemini, Claude, Ollama, Llama.cpp, Codestral, and more.

384 stars+1 this week

Production-ready open source terminal coding agent with readable, layered code: permission rules, OS sandboxing, MCP, skills, sub-agents, and Anthropic, OpenAI-compatible, Gemini, or local models.

1,024 stars+5 this week

Universal, model-agnostic operating harness for AI agents (Claude, Codex, Gemini, …) — a lean core + work-type profiles assembled by one setup script.

152 stars-2 this week

Taking the pi coding agent to Claude Code-level performance: 0.539 → 0.773 pass@1 on Terminal-Bench 2.1 with the same self-hosted 27B model, by re-engineering the agent.

186 stars0 this week

A virtual pet companion for your AI — Designed to provide in-context code review feedback with personality. Grow with your buddy and level up together. Works with Claude Code, Codex, CursorCLI, Github CopilotCLI, OpenClaw, and any MCP compatible clients

119 stars+1 this week

Turns vibe coding into high quality code. Sets up rules and gates in your repo so AI-written code stays correct without you reviewing every line.

180 stars0 this week

个人 Pi 编程智能体配置：17 插件 + 18 全局技能 + 2 MCP 与一键安装脚本 / Pi coding agent full configuration

194 stars+1 this week

OpenCode++: a Coding Agent Reliability Harness for OpenCode, adding context, edit boundaries, command evidence, verification gates, impact analysis, and repair loops.OpenCode++：面向 OpenCode 的 AI 编程可靠性增强框架，为其增加上下文管理、编辑边界、命令证据、验证门禁、影响分析与修复闭环能力。

113 stars0 this week

A copy-paste system prompt that has your coding agent (Claude Code, Codex, Cursor) build a self-improving agent system for any computer work.

884 stars+2 this week

Curated skills, profiles, and config templates that supercharge Codex CLI — multi-model, deep research, image gen & browser automation.

249 stars+2 this week

Local-first native macOS terminal with Vietnamese IME support and coding-agent observability

183 stars0 this week

A local desktop control center for organizing Codex projects, engineering tasks, sessions, Git changes, Skills, and MCP configuration.

191 stars0 this week

AI-powered code assistant for Vim. OpenAI and ChatGPT plugin for Vim and Neovim.

1,190 stars+3 this week

面向 AI 上下文管理的 Agent Skill：为 Codex 上下文管理、Cursor 上下文切换和 Claude 上下文管理提供跨窗口续接，用 Git 保存可验证的功能说明与变更记录。AI coding context management and agent handoffs.

104 stars0 this week

A workflow harness that helps AI coding agents plan, review, test, and ship safer code.

208 stars0 this week

Opinionated AI coding agent and dev environment automation for macOS

142 stars0 this week

Code search MCP for Claude Code. Make entire codebase the context for any coding agent.

12,678 stars+18 this week

The open source coding agent for your terminal.

373 stars0 this week

Your AI forgets. This remembers. Spec-driven coding harness for vibecoders, product owners, CEOs and real builders — self-improving context memory, 15 agents, 33 skills working with /goal, agent-team, & workflow on autopilot loops with 0 need for human gate. Kills context rot, ships features, not spaghetti. Claude Code & Codex. Any stack

1,168 stars+6 this week

Watch, approve and steer your coding agents from your phone.

117 stars0 this week

On-demand Linux computers you can hand to an AI — real Firecracker microVMs with a browser, terminal, coding agents, and an AI that drives them.

346 stars+1 this week

Production-grade Agent Skills for AI coding agents—composable workflows for planning, TDD, debugging, review, UI/UX, releases, incidents, and evals.

100 stars+1 this week

A manifesto and playbook for AI-native software engineering in the LLM era / AI-Native的软件工程宣言

327 stars+5 this week

This project is a plugin for LM Studio that provides a rich set of tools to a large language model. It allows the LLM to interact with your local file system, execute code, access the internet, and more. This empowers the LLM to perform complex tasks like code generation, project scaffolding, and web research.

130 stars0 this week

🦦 ADHDev — Agent Dashboard Hub. Monitor & control AI coding agents from a single dashboard. Self-hosted, open-source.

117 stars+1 this week

Uncensored AI coding agent in your terminal. Does the work, skips the sermon. 256K context, crypto-only billing, no card on file.

109 stars-4 this week

Agentic Coding Rules, Templates etc...

169 stars+2 this week

An educational AI coding agent CLI

305 stars0 this week

extendable code review and QA agent 🚢

2,521 stars+6 this week

仓库原生 AI Coding Harness —— 把一次性 AI 对话变成可治理、可验证、可沉淀的工程闭环 · spec-first.cn

110 stars0 this week