Awaiting qualifying evidence
Open-source projects. Community-powered coins.Last checked Oct 9, 2026 · 04:19 AM
>_ AI AGENTS FOR GITHUB PROJECTS
Small beginnings.
Big possibilities.
Research. Launch. Onboard.
Give your agent a mission. Find and research GitHub projects, launch your chosen coin, and bring the builders on board—all in one place.
Try a direction
Open-source projects Your wallet. Your final say.
01 / Discover02 / Research03 / Launch04 / Onboard
Choose its mind6 premium models
THE SEED WORKFLOW
Your next idea, from start to finish.
- 01
Discover
Tell your agent what you’re looking for. Find GitHub projects that match your interests and brief.
- 02
Research
Compare demos, code activity, developer profiles and social evidence. Review the shortlist and choose your project.
- 03
Launch
Review the creator-reward split, then approve your Pump.fun launch with your wallet. Your coin gets its own SEED page.
- 04
Onboard
Bring developers in with email and X introductions, their coin page and a guide to claiming creator rewards.
From the communityDiscover
35.8K2.5K
Checking scanner statusGitHub: public accessSocial: limited coverage
FOLLOW THE SIGNAL
Standout projects, easier to find.
Explore the strongest measured signals across the full directory.
Awaiting qualifying evidence
Awaiting qualifying evidence
Awaiting qualifying evidence
Awaiting qualifying evidence
FIND YOUR NARRATIVE
What are you into?
DISCOVER / RESEARCH / LAUNCH
Fresh picks · every 30 minutes
Showing saved project records while the latest directory loads.
Showing 1–20 of 117 projects · Page 1 of 6Page one rotates every 30 minutes. All projects remain searchable.
DeepSeek-Reasonix
A reliable coding agent for complex software engineering tasks.
WHY NOW
A fresh catalyst has not been verified
claude-plugins-official
Official, Anthropic-managed directory of high quality Claude Code Plugins.
WHY NOW
A fresh catalyst has not been verified
openharness
The ultimate harness for coding agents and beyond. All your agents. All your machines. One command center. Start with code, then follow your curiosity and build across disciplines: CAD, circuits, robots, games and music.
WHY NOW
A fresh catalyst has not been verified
dreamerv3
Mastering Diverse Domains through World Models
WHY NOW
A fresh catalyst has not been verified
VoiceStudio
VoiceStudio is the open-source, fully-local ElevenLabs alternative — voice cloning, voice design, video dubbing, dictation, transcription & audiobook creation in 646 languages.
WHY NOW
A fresh catalyst has not been verified
lidar_slam_ros2
ROS 2 LiDAR SLAM for pointcloud-map authoring, benchmarking, and Autoware-compatible map workflows.
WHY NOW
A fresh catalyst has not been verified
overtime
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.
WHY NOW
A fresh catalyst has not been verified
nanocodex
Building blocks for frontier OpenAI agents in Rust. Nanocodex empowers you with Codex-level performance anywhere.
WHY NOW
A fresh catalyst has not been verified
scientific-agent-skills
Turn any AI agent into an AI Scientist. The #1 Agent Skills library for science, used by 250,000+ scientists worldwide. 177 ready-to-use validated skills plus 100+ scientific databases covering biology, chemistry, medicine, and drug discovery. Compatible with Cursor, Claude Code, Codex, Pi, Antigravity, and the open Agent Skills standard.
WHY NOW
A fresh catalyst has not been verified
KiroCrew
A persistent workspace for development work that self-improves and continues beyond one session.
WHY NOW
A fresh catalyst has not been verified
stop-that-shit
Stop That Shit（别再造史了）｜面向 Codex/GPT 场景的多平台 Hook + Skill Guard：拦截 AI coding agent 无需求的哈希、校验和与任务范围膨胀。 A multi-platform Hook + Skill Guard for AI coding agents in Codex/GPT workflows: stop unrequested hashes, checksums, and task-scope creep.
WHY NOW
A fresh catalyst has not been verified
claude-code-changelog
Tracking prompts, feature flags and metadata of Claude Code releases. Subscribe to ↓
WHY NOW
A fresh catalyst has not been verified
context-mode
Context window optimization for AI coding agents. Sandboxes tool output (98% reduction), persists session memory, and enforces routing across 17 platforms via MCP + hooks.
WHY NOW
A fresh catalyst has not been verified
okou
Okou connects to the tools your team already uses and does the work — across marketing, sales, engineering, and operations, under your control.
WHY NOW
A fresh catalyst has not been verified
oneshot-gtm
GTM agent for technical founders. Pay-per-result. Two surfaces: terminal CLI + local web dashboard.
WHY NOW
A fresh catalyst has not been verified
qwen-code
An open-source AI coding agent that lives in your terminal.
WHY NOW
A fresh catalyst has not been verified
edgeever
AI-native knowledge base & Evernote/Obsidian alternative with instant sync & native MCP. Free on Cloudflare or self-hosted via Docker.
WHY NOW
A fresh catalyst has not been verified
ghidra-mcp
Ghidra MCP Server — 200+ MCP tools for AI-powered reverse engineering. GUI plugin + headless server, lazy tool loading, convention enforcement, batch operations, Ghidra Server integration, and Docker deployment.
WHY NOW
A fresh catalyst has not been verified
superpowers
An agentic skills framework & software development methodology that works.
WHY NOW
A fresh catalyst has not been verified
How the shortlist is scored 80+ shortlist · 90+ standouts
We scan GitHub Trending, game and AI topics, and recent X posts linking directly to repositories. Discover opens with small themed collections; the full catalogue stays searchable. Minecraft and GTA collections describe community connections, not official game affiliation.
25 source quality: license, README, actual source, tests and CI files. 15 active development: recent code pushes. 15 adoption: capped stars and forks. File presence is not a passing test run or an audit.
20 demo & theme: real project demos, screenshots, artwork and a recognizable use case. Generic link cards earn no media points. 15 GitHub momentum: fresh Trending placement and measured star/fork growth. 10 social traction: recent measured X reach, independent posting accounts and engagement.
The shortlist requires an actual project visual, source-quality evidence and an earned score of at least 80. Scores of 90+ are the strongest current signals. Developer contacts and fee eligibility are checked separately before launch. We do not raise low scores to fit the shortlist. Missing or stale data earns no points for that factor; social views remain unknown when unmeasured. These are repository research scores, not predictions of coin returns.
Instagram and TikTok metrics are not connected. GitHub Trending · X metric source