生成、审查、测试、DevOps、迁移与应用构建
平均值只计算有观测的数据；未知值不按 0 分计入。
A persistent workspace for development work that self-improves and continues beyond one session.
A persistent workspace for development work that self-improves and continues beyond one session.
Open-source AI coding agent for the terminal. Claude Code-grade accuracy with smart model routing — uses the right AI model for each task, cutting costs 10x. Supports Claude, GPT, Gemini, DeepSeek & more.
Memcode is an agentic coding CLI that builds a persistent model of your codebase for better context and memory. Install in one line.
Terminal-first, knowledge-grounded multi-agent software delivery pipeline: scope requirements, implement changes, run tests, and gate pull requests with deterministic QA and ensemble code review.
Open-source app builder engine — intent to working app
Pi — A cross-platform AI coding agent, bringing the Claude Code experience to your desktop. No environment setup, no terminal commands. Download and start coding right away.
Easily turn any data source or API you manage into a fully compliant MCP server to use with your AI tools, agents, and LLMs.
Per-user cost dashboards from Claude Code's built-in OTel
Non-destructive compression gateway that cuts AI coding-agent token bills 25% on a single turn, climbing past 60% across long multi-turn sessions and past 85% in context-saturated deployments. Powered by the first open-source code-native 4B compression model. Drop-in for Claude Code, Cursor, Codex, OpenHands. No agent code changes.
persistent Linux workstations for AI
Your coding agent can now edit videos
open-source multi-agent terminal deck that abstracts memory
I built an agentic platform that writes and ships code
Production-grade Agent Skills from Evil Martians — drop-in expertise for your AI coding agent
One Shared Memory for Claude Code, Cursor and Codex (MCP)
A IDE and ADE merging agent worktrees with native tooling
fixes Fable 5
Generative UI for Claude Code, Codex, and Gemini CLI
Multi-agent AI coding factory for one person — Claude Code PM + Codex/Qwen/Grok/Kimi/AGY writers, durable conveyor, auto-merge to main
Turn Codex threads into an organization of long-lived domain agents.
to-end
Use ChatGPT Web (including Pro) as a native model in the Codex app — with context, tools, streaming and images beyond Codex usage limits.
fast Prime Agent fork with Bun REPL
Local file search with citations for AI agents. No cloud uploads.
A coding harness/agent beating Claude Code itself on Sonnet
the model writes its own multi-agent workflow, then runs it
AI-native code review assessments for engineering hiring
Persistent, structured project memory for Claude Code and Codex - event-sourced, typed, fail-open. Your agent stops re-deciding what you already decided. - KanishkNoir/cognikernel
给纯文本 LLM agent 装上眼睛：图片问答、OCR、截图分析、视觉定位等一套视觉工具箱 + skill，并可无缝接入 Codex、Claude Code、OpenCode、Pi ｜ Give text-only LLM agents vision: image Q&A, OCR, screenshot understanding, visual grounding, image-to-SVG - a vision toolkit & skill, with drop-in integration for Codex, Claude Code, OpenCode, Pi
BREAD: one vocabulary, two operators. A no-build, AI-native web stack: batch (substrate) · grain (design system) · mill (CMS) · proof (plan board) · crumb (guided tours).
Your agents already solved this. deja finds it — it indexes the sessions your coding agents already wrote to disk, months of history from before you installed it, and recalls them automatically at session start across seventeen harnesses. 84.9% hit@1 on LongMemEval-S, no LLM, no embeddings. One zero-dep binary, fully local.
Your agent reads the rules. This checks whether it followed them.
Share agent skills across repos with per-project lockfiles
Codex writes the code, Claude reviews it
Give your AI a persistent, reusable UI — it builds the component once, you keep it forever. An open MCP App engine.
Free, MIT alternative to paid Django schema review. Blast radius on every PR, schema drift, N+1 across functions, ER diagrams, MCP server. No DB, no Django boot, no Pro tier.
Bullet is a really fast coding agent with a leaner orchestration layer.
first coding agent workbench with secretless microVMs
no root
Run Claude Code agents in parallel without losing context
Run many Claude Code (or Codex) sessions in parallel — across every project — from one screen. Local-first, git-worktree-isolated tasks, no API key.
See what your coding agents did and what it cost. Breaks each task down into work steps — tools used, files changed, tests run, time and tokens spent. Local-first dashboard for Claude Code, Codex, OpenCode, and more. No login, no telemetry.
Persistent, provider-neutral memory for Codex, Claude Code, OpenCode, Pi, and MCP coding agents.
Native, local-first knowledge graph engine for code and project artifacts—inspired by Graphify, built in Rust, and evolving beyond it.
An egress gate for CLI coding agents. Masks secrets and customer data in the request body before it reaches the model provider, and the agent keeps working. - softcane/hamza
Chrome extension that clusters GitHub PR diffs into review units with summaries. Free, open source, bring your own LLM key.
a Claude-native terminal for macOS that popup like Spotlight
Agent Skills official site
MCP server + CLI that puts a real human in your coding agent's loop. It publishes work mid-task, a reviewer pins what's wrong and returns a verdict, and the agent iterates until approved.
source control room for AI coding agents
Small Version of Claude Tag
Leave comments on your live app. Your coding agent resolves them. - montanaflynn/agent-feedback
macOS-first local MCP and Actions runtime that gives ChatGPT real coding hands over trusted projects
A terminal session manager for Claude Code, and more
Fast, interruptible verification browser for AI coding agents: 35 ms checks, pixel diffs, live human hand-off
A package manager where packages are agent tasks
Mission control for every Claude Code session on your machine.
Native macOS orchestrator for coding agents — run Claude Code, Codex, Cursor, Gemini and shells in parallel across git worktrees and remote hosts
an append-only log of what your AI agent already rejected
A safe-by-default, batteries-included Claude Code harness starter pack — guardrails, a wiki-grounded quality loop, and a memory lifecycle. - choiyounggi/groundwork
Security guidance based on library and version for developers and agents. - Reware-Labs/securitycards
Codex skill for auditing and tuning Codex Desktop context/tool surfaces
looping during GitHub outages
account now works on macOS too
An Opinionated workflow for building with AI
Metrik 是一款桌面常驻工具，统一查看本机各个 AI 编程 Agent 的官方配额余量与 Token 消耗，支持 ChatGPT、Claude、GLM、Kimi 等主流 Agent。
Claude Code's remote session gives up reconnecting in 31s
coding agents collaborate across companies
see what compaction dropped from an agent session
A little badge for your Claude Code projects
runs anywhere. uses anything