Most wanted
Where the pain is: harnesses whose open issues collect the most 👍, and the single issue people want most.
| # | Project | Most-wanted issue | Stars | Δ 7d | Δ 30d | 90d trend | Age | Lang | Last push |
|---|---|---|---|---|---|---|---|---|---|
| 1 | anthropics/claude-code Claude Code is an agentic coding tool that lives in your terminal, und… | Bring Back Buddy — A Consolidated Plea from the Community+1176 👍 · 13,550 open | 144.0k | +751 | +3,691 | 1 yr | Python | 11h ago | |
| 2 | openai/codex Lightweight coding agent that runs in your terminal | LSP integration (auto-detect + auto-install) for Codex CLI+475 👍 · 15,005 open | 121.4k | +2,002 | +17,364 | 1 yr | Rust | 48m ago | |
| 3 | anomalyco/opencode The open source coding agent. | [FEATURE]: Allow to expand the pasted text (e.g. `[Pasted ~1 lines]`)+236 👍 · 4,153 open | 203.7k | +1,621 | +10,096 | 1 yr | TypeScript | 23m ago | |
| 4 | google-antigravity/antigravity-cli Antigravity CLI brings the reasoning, execution, and orchestration cap… | Feature request: add ACP (Agent Client Protocol) stdio JSON-RPC mode+388 👍 · 636 open | 2.1k | +84 | +312 | 3 mo | — | 7h ago | |
| 5 | Aider-AI/aider aider is AI pair programming in your terminal | MCP SUPPORT+196 👍 · 1,367 open | 48.7k | +185 | +782 | 3 yrs | Python | 104d ago | |
| 6 | continuedev/continue open-source coding agent | Neovim support needed+245 👍 · 456 open | 35.8k | +96 | +426 | 3 yrs | TypeScript | 36m ago | |
| 7 | google-gemini/gemini-cli An open-source AI agent that brings the power of Gemini directly into… | Add gemini-3.1-pro-preview+111 👍 · 583 open | 106.8k | +86 | +437 | 1 yr | TypeScript | 9h ago | |
| 8 | manaflow-ai/cmux Open source Ghostty-based macOS terminal with vertical tabs and notifi… | Linux support?+162 👍 · 1,822 open | 26.8k | +235 | +1,160 | 7 mo | Swift | 8m ago | |
| 9 | github/copilot-cli GitHub Copilot CLI brings the power of Copilot coding agent directly t… | 11.1k | +17 | +81 | 3 yrs | Shell | 8h ago | ||
| 10 | BerriAI/litellm The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ L… | 58.0k | +550 | +2,410 | 3 yrs | Python | 55m ago | ||
| 11 | headroomlabs-ai/headroom Compress tool outputs, logs, files, and RAG chunks before they reach t… | [FEATURE] headroom wrap opencode — CLI wrapper for OpenCode+112 👍 · 292 open | 68.9k | +1,005 | +3,960 | 8 mo | Python | 6h ago | |
| 12 | charmbracelet/crush Glamourous agentic coding for all 💘 | 27.9k | +146 | +812 | 1 yr | Go | 2h ago | ||
| 13 | Tiger3807861189/J-Space-Cognition-Suite-V3.7 J-Space Cognition Suite V3.7 - AI cognitive-enhancement Skills based o… | [补档] 下次让 AI 编纂报告的时候注意常识+82 👍 · 35 open | 3.0k | +6 | — | 1 mo | Python | 1d ago | |
| 14 | strands-agents/harness-sdk Build an agent harness and control it end-to-end. Open-source SDK for… | [FEATURE] Request to Develop a Go SDK for Strands+90 👍 · 484 open | 7.2k | +114 | +349 | 1 yr | Python | 3h ago | |
| 15 | NousResearch/hermes-agent The agent that grows with you | 241.2k | +3,638 | +15,386 | 1 yr | Python | 1h ago | ||
| 16 | code-yeongyu/oh-my-openagent OmO: Drop your tokens. Ultrawork. Done. | [Feature]: Disable oh-my-opencode via cli command+52 👍 · 522 open | 68.7k | +214 | +1,400 | 9 mo | TypeScript | 14m ago | |
| 17 | datacurve-ai/deep-swe Measuring frontier coding agents on original, long-horizon engineering… | 1.6k | +85 | +284 | 3 mo | Python | 8d ago | ||
| 18 | Mintplex-Labs/anything-llm Stop renting your intelligence. Own it with AnythingLLM. Everything yo… | [FEAT]: Fine-Grained Access controls+59 👍 · 300 open | 65.6k | +282 | +1,238 | 3 yrs | JavaScript | 10h ago | |
| 19 | stablyai/orca Orca is the ADE for working with a fleet of parallel agents. Run any c… | [Feature]: Jujutsu Workspaces+32 👍 · 2,510 open | 61.4k | +5,679 | +23,574 | 5 mo | TypeScript | 10m ago | |
| 20 | chroma-core/chroma Search infrastructure for AI | [Feature Request]: Hybrid Search with BM25+78 👍 · 337 open | 29.2k | +49 | +262 | 3 yrs | Rust | 14h ago |
Ranked by 👍 reactions on open issues, not by how many issues are open — a raw issue count mostly tracks how big a project is. We check the top issues of every harness above 500 stars, so smaller projects are not represented here.
Methodology
We find candidates through GitHub Search (agent-related topics and keywords, plus a radar for repos younger than 90 days), then snapshot every repo in the pool once a day via the GraphQL API. For new entries we rebuild star history from sampled stargazer timestamps.
Fast growing ranks by (2 × stars_7d + stars_30d) × youth_bonus. Last week counts double, and young repos get a boost so giants don't bury newcomers. The other rankings sort by stars, by repo age, and by 👍 reactions on open issues.
Exclusions:archived repositories, inactive repos (no pushes in 60 days), awesome-lists, and prompt collections. We define a “harness” as a tool or framework that orchestrates an LLM to complete tasks — tool calling, context management, agentic loops. Models themselves, API wrappers, and prompt libraries do not qualify.