Fully autonomous & self-evolving research from idea to paper. Chat an Idea. Get a Paper. 🦞
- autonomous-research
- citation-verification
- llm-agents
- multi-agent-debate
Repository Index
81,588 visible repositories in the index
1–24 of 24 · Most stars
Strip AI-writing tells from papers and grant proposals (NSF/NIH), while keeping scholarly voice and tying claims to evidence. A skill for Claude Code, Codex, and MorphMind.
- academic-writing
- grant-writing
- llm
- nih
[ICML'26] SimpleMem: Efficient Lifelong Memory for LLM Agents — Text & Multimodal
OpenDeepWiki is the open-source version of the DeepWiki project, aiming to provide a powerful knowledge management and collaboration platform. The project is mainly developed using C# and TypeScript, supporting modular design, and is easy to expand and customize.
- chatgpt
- deepwiki
- docs
- fine-tuning
🦞 Just talk to your agent — it learns and EVOLVES 🧬.
A project structure aware autonomous software engineer aiming for autonomous program improvement. Resolved 37.3% tasks (pass@1) in SWE-bench lite and 46.2% tasks (pass@1) in SWE-bench verified with each task costs less than $0.7.
Agentic AI Hedge Fund OS (AIMM)
- trade-bot
- trade
- multiagent-systems
- agentic-trading
美股与全球市场数据工具包（给 AI 编程助手用）：官方源优先、零鉴权、标注合规级别 | US & global market data for AI coding assistants — zero-auth, official sources. CBOE options + 0DTE, VIX term structure, FINRA short data, SEC Form 4/13F, central-bank rates & FX, Taiwan exchanges, EIA energy, BLS US macro & jobless claims. 17 layers, 50+ endpoints, 18 sources, each compliance-tiered.
- 0dte
- ai-skill
- cboe
- claude-code
OpenCodeInterpreter is a suite of open-source code generation systems aimed at bridging the gap between large language models and sophisticated proprietary systems like the GPT-4 Code Interpreter. It significantly enhances code generation capabilities by integrating execution and iterative refinement functionalities.
Translated🍔 Maimen Certification Machine (麦门认证机) — Upload any image and the AI will identify your Maimen (McDonald's fan community) status: a certification meme card + meal recommendations based on real nutrition data + one-click coupon claiming. Entry for the 2026 McDonald's Programmer Creative Development Contest
TranslatedArmor-breaking (jailbreak) experiment project targeting GPT 6.0 and workbuddyV4.1flash
TranslatedEvidence-chain whiteboard + MCP server for AI research agents: every claim traces back to the run and code that produced it. When an AI agent does research, every conclusion can be traced back to the code that produced it. Claude Code · Codex · Cursor · Gemini CLI
Open-source, AI-assisted UI design review for coding agents. Inspect screenshots, scope code changes and compare results in a local workbench. Alpha.
- coding-agents
- design-review
- design-systems
- developer-tools
A Claude Code skill for clean, honest dashboard UI: KPI tiles, charts, date pickers, ranked lists, states, layouts and a screenshot QA pass. Distilled from 127 shipped dashboards.
- agent-skills
- analytics
- claude-code
- claude-skill
FOREST is a research agent for long-horizon science, where evidence gets lost, errors compound, and goals drift. It explores ideas, reads literature, forms hypotheses, runs real experiments, analyzes results, revises paths, and builds a full paper—all in an editable graph you can inspect, branch, redirect, with claims and figures linked to evidence
- ai-agents
- ai-scientist
- automated-research
- autoresearch
Multi-agent research execution system: paper reproduction, benchmark evaluation, AutoResearch and claim-evidence graphs
- auto-research
- golang
- multi-agent
- paper-reproduction
TranslatedLet your AI deliver more value | ChatGPT project context integration, multi-model collaboration and cross-review across Codex / Claude Code and APIs, with unified account quota and session management
Translated麦门情报站 (Maimen Intel Station, "McDonald's gate intelligence station") | A Skill based on McDonald's MCP for daily promotions, coupons, and points reminders, under development.
(THIS IS THE PUBLIC VERSION) Muse-by-Meta usage audit companion designed for those who want to understand Muse’s actions during a multi-step task without pretending to have telemetry they can’t actually access.Check out Muse, your personal AI agent. Code: 5F2V31 https://muse.ai/join
- meta
- metaai
- metaai-api
- metaai-download
TranslatedMaimen All-in-One Butler (麦门, Maimen): a one-stop assistant based on McDonald's China's official MCP — automatic coupon claiming, authoritative price comparison, ordering recommendations, daily inspections, and a Big Mac Index. An entry in the 2026 McDonald's Programmer Festival Creative Development Contest.
- mcdonalds
- mcp
- mcp-skill
- model-context-protocol
TranslatedMcDonald's MCP skill: list of orders pending review, progress toward good-review gift redemption, order top-ups to reach the invoice reimbursement threshold, single lucky draw confirmation. 99 tests, unofficial product.
Translated麦门心事 (Maimen Xinshi, "McDonald's Gate Heart Matters"): Read a single line of worries as a McDonald's meal, then let three strangers decide whether you should eat it. A Skill based on the McDonald's China MCP, plus a zero-dependency single-file demo page.
Catch your AI agents when they lie about what they shipped — verifies claims against git instead of believing the agent.
- agent-orchestration
- cli
- developer-tools
- llm-agents
Per-repo memory, outcome telemetry, and a calibrated-confidence gate for Claude Code, with MCP and AGENTS.md projections so other AI coding tools can read its context. Notes survive sessions; success claims need test evidence; your reverts are remembered. Local-only, stdlib runtime.