AI-powered bot duo for code gen, refining, web search, GitHub imports, file mgmt & Python libs, enabling a dynamic coding experience.
Repository
Repository di ruvnet
Autonomous Feedback Loops: AIConverse is an innovative project focused on utilizing AI-powered feedback loops.
AI-powered game engine for dynamic, personalized experiences in evolving worlds. Ethical, accessible, inclusive.
Agent Name Service (ANS) Protocol, introduced by the OWASP GenAI Security Project, is a foundational framework designed to facilitate secure discovery and interaction among AI agents.
A multiplayer ai community where humans hang out in a web app and agents connect over SSH or MCP — sharing the same message boards, marketplace, doors, and a competitive benchmark Arena.
Automated Code Generation and Testing with OpenAI Codex and GitHub Integration built in Rust
AI Hackerspace Consulting Collective (AiHCC)
AI-TOML Workflow Specification (aiTWS), a comprehensive and flexible specification for defining arbitrary Ai centric workflows.
An experimental open-source attempt to make GPT-4 fully autonomous.
The ultimate bot generator bot prompt. Use this prompt to create powerful ChatGPT bots for anything you can imagine.
CVE-bench — conformant reproduce-and-fix security benchmark from public CVEs + OSS fix-PRs/tests. Apply-patch -> run the security test (FAIL->PASS). Cost-Pareto leaderboard, PR-based submissions, nightly CI.
A trading script for KuCoin that continuously places buy and sell orders based on market data and a predictive model by OpenAI's GPT-3.5
An experimental open-source attempt to make GPT-4 fully autonomous.
A debugging and control layer for embodied graph systems — cut the wiring, measure the fracture, ask what structure made the failure inevitable.
Visual planning and context control for shipping big apps with AI coding. Build from scratch or map existing repos. Dossier maps user workflows, sets agent context per feature, builds, tests and ships from one interface.
FACT – Fast Augmented Context Tools: FACT is a lean retrieval pattern that skips vector search. We cache every static token inside Claude Sonnet‑4 and fetch live facts only through authenticated tools hosted on Arcade.dev. The result is deterministic answers, fresh data, and sub‑100 ms latency.
Agentic Engineering for Data Analysis