75,859 visible repositories in the index
49–64 of 64 · Most stars
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
Neuro-symbolic agents with verified memory. MCP math tools, an algebra repair Skill, and an open challenge. Verify solutions, learn checked rules, and reuse.
Autonomous OODA-loop pentesting agent. Hermes brain, Kali + Playwright tools over MCP, ATT&CK as the Orient language.
The first exam for code agents in the physical world: frozen robot tasks from many benchmark suites, each answered with a program and verified in a separate sandbox. Runs on Harbor.
Vim Plugin For ChatGPT
Runtime defense against memory poisoning in AI agents (OWASP ASI06). Drop-in for LangChain, OpenAI Agents, AutoGen, CrewAI and mem0.
Medical LLM agent and MRI segmentation workspace built on PharmaLLM, with LangGraph, vLLM, and BEU-Net.
HarnessMM: recursive self-improvement for harness token efficiency
A minimal set of agent workflows and tools for robotics
DiscoveryRSI: Recursively Learning to Discover Valuable Hypotheses
Translated🍟 McD Saver (麦麦省钱助手, "McDonald's money-saving assistant") — a money-saving ordering Agent Skill built on McDonald's China's official MCP: real-time price verification via the official calculate-price, coupon combination optimization, sunk-cost check-up and multi-order coupon scheduling, and final prices calculated on the same basis across four channels: official coupons, set meals, group-buy vouchers, and points. Online price estimation without login.
Autonomous DFIR agent: point it at disk images, memory dumps or log exports and get back an investigation that shows its work. Volatility 3, Plaso, YARA and any OpenAI-compatible LLM.
Fault-injected tool environments with side-effect grading for evaluating and post-training LLM agents
Nosis is a lightweight personal agent runtime: per-session execution boundaries with OS-level sandboxing, computer use, a full built-in toolset, Skill / Plugin / MCP extensions, one runtime shared by GUI and TUI, and file-persisted sessions, plans, and memory.
MCP server for spatial transcriptomics analysis through natural language interfaces.
Catch your AI agents when they lie about what they shipped — verifies claims against git instead of believing the agent.