claude-code
Tracked open-source repos tagged claude-code, sorted by stars.
- #361
Delegate a coding task to a separate coding agent CLI, review the diff, land the commit yourself — one per implementer.
★ 1,611+0Star change over the last 7 days - #362
Lightweight coding agent written in Rust, optimized for memory footprint and performance
★ 1,611+0Star change over the last 7 days - #363
Web, Desktop & Mobile client for Codex, Claude Code, OpenCode, Kimi, Augment Code, Qwen, fully end-to-end encrypted
★ 1,610+0Star change over the last 7 days - #364
Topic → 4K narrated video for coding agents. v4.0: all TTS via the ttsCN engine component (11 platforms incl. MiniMax voice clone, native word-level subtitle sync), manifest-based Asset Engine, Remotion composition, cost-gated AI generation
★ 1,599+0Star change over the last 7 days - #365
Ghostty Blackhole puts a real, ray-traced black hole inside your terminal. It grows as Claude Code's context window fills up, live. A fresh session is a quiet hole in the corner. A full one swallows half your screen. You'll always see /compact coming.
★ 1,590+0Star change over the last 7 days - #366
List of agent orchestrators
★ 1,587+0Star change over the last 7 days - #367
Spec-Driven Development for serious software developers. Spec Coding with with Claude, Cursor, Gemini, Codex. Kanban dashboard, git worktrees, auto-merge and more.
★ 1,582+0Star change over the last 7 days - #368
Your infinite canvas workspace for agents, tasks, knowledge, and research. An infinite canvas for Claude Code, Codex, terminals, tasks, and notes.
★ 1,576+0Star change over the last 7 days - #369
ktx is an executable context layer for data and analytics agents 🐙 Allow Claude Code, Codex, or other AI agents to query analytical databases accurately and with full context of your company
★ 1,571+0Star change over the last 7 days - #370
Claude reads its own source code — 17-chapter architectural deep-dive into Claude Code v2.1.88. EN/ZH bilingual.
★ 1,569+0Star change over the last 7 days - #371
High-performance OpenAI and Anthropic compatible LLM inference server for Apple Silicon. Native MLX, continuous batching, multimodal models, MCP tool calling, and Claude Code support.
★ 1,557+0Star change over the last 7 days - #372
Run Coding Agents in Sandboxes. Control Them Over HTTP. Supports Claude Code, Codex, OpenCode, and Amp.
★ 1,556+0Star change over the last 7 days - #373
A ready-to-fork Claude Code template for academics using LaTeX/Beamer + R. Multi-agent review, quality gates, adversarial QA, and replication protocols.
★ 1,549+0Star change over the last 7 days - #374
Open-source, local-first conversational AI video editor with a professional multi-track timeline, Agent Skills, MCP integration, and Remotion rendering.
★ 1,542+0Star change over the last 7 days - #375
Persistent project memory for AI coding agents. Structured scaffold + drift detection CLI.
★ 1,540+0Star change over the last 7 days - #376
Cookiy AI Skill for AI agents (Claude, Codex, Cursor, OpenClaw) — end-to-end user research: AI interviews, synthetic users, quant surveys, participant recruitment.
★ 1,532+0Star change over the last 7 days - #377
A cross-platform desktop app to manage Agent Skills in one place and sync them to multiple AI coding tools’ global skills directories — “Install once, sync everywhere”.
★ 1,528+0Star change over the last 7 days - #378
ADR secures enterprise AI agents through observability, security benchmarking, and threat detection. Deployed at Uber.
★ 1,527+0Star change over the last 7 days - #379
A pre-execution guard for AI coding agents. It blocks destructive Git and file system commands, plus common attempts to access sensitive files, before a tool call runs. Supports Amp Code, Antigravity CLI, Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot CLI, Grok Build, Hermes Agent, Kimi Code, OpenClaw, OpenCode, and Pi.
★ 1,521+0Star change over the last 7 days - #380
High-performance code-intelligence engine for AI agents and IDE, supports 257 languages, multi repositories, based on graph, with access via CLI, MCP Server, and API. AI coding agents teammate - expose only needed information, cutting token usage up to 50x. 100% local. Discord: https://discord.gg/39MFHu3J5d
★ 1,517+0Star change over the last 7 days - #381
Agent skill to turn any arxiv paper into a working implementation
★ 1,517+0Star change over the last 7 days - #382
US stock market data for AI coding assistants — zero-auth, official sources. CBOE options with full Greeks + 0DTE flow, FINRA market-wide short volume, SEC EDGAR filing stream, and a free market-wide screener. 13 layers, 30+ endpoints, 11 sources. Every source labeled with its compliance tier.
★ 1,512+0Star change over the last 7 days - #383
AI 短剧/漫剧创作 skill 合集,覆盖剧本、资产、分镜、图片/视频提示词到独立审查全链路,适配 Claude Code 与 Codex。| An AI short-drama skill suite for Claude Code & Codex: scripts, assets, storyboards, image/video prompts, and independent review.
★ 1,498+0Star change over the last 7 days - #384
Local-first AI token usage & cost tracker for 31 coding tools incl. Claude Code, Codex, Cursor, Gemini & DeepSeek Harness—with native apps. Never reads prompts.
★ 1,497+0Star change over the last 7 days - #385
resume any AI coding session in another tool — Claude Code, Copilot, Gemini, Codex, Cursor
★ 1,480+0Star change over the last 7 days - #386
Cross-vendor messaging for CLI AI coding agents — let Claude Code, Codex, Gemini & Copilot talk to each other in one team. Bash + SQLite, no daemon, no framework.
★ 1,477+0Star change over the last 7 days - #387
Node-based terminal manager for AI coding agents — tmux-backed terminals and parallel agent sessions as draggable nodes on an infinite pan/zoom canvas. macOS, Linux, and a browser Server Edition.
★ 1,474+0Star change over the last 7 days - #388★ 1,474+0Star change over the last 7 days
- #389
🏄🏼♂️ The blackboard for coding agents - agentic development environment for claude code, codex, cursor, opencode, grok and more.
★ 1,469+0Star change over the last 7 days - #390
The long-horizon computer-use harness. Run AI agents across desktop apps and the CLI for extended periods while preserving task state and making reliable progress on complex workflows. Features fresh-context execution, durable verified state, independent auditing, recoverable progress, and native Claude Code / Codex / OpenClaw integration.
★ 1,454+14Star change over the last 7 days