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.
- ai-agents
- benchmark
- coding-agents
- embodied-ai
47,133 repositories indexed
49–72 of 72 · Most stars
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.
Agent skills for shipping real products with coding agents, from the first idea to paying users. No coding.
The World's Most Comprehensive, Authoritative, and Structured Open Source Data Source Knowledge Base
First-class patterns for Clojure. Made with love, functions, and just the right amount of syntax.
BotWave - Your Raspberry Pi FM Network
Universal LLM router for AI coding tools. Works with Claude Code, Cursor, Codex, Gemini CLI, Copilot and more. Free-first fallback chain cuts costs 35-80%.
Credential gateway for AI agents. Log in once via Oauth2 or API Key. Every agent stays authenticated — headless, no SaaS, agents never see your credentials.
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.
In this project, the Pacman agent will find paths through his maze world, both to reach a particular location and to collect food efficiently. I implemented general search algorithms such as depth-first, breadth-first, uniform cost, and A* search algorithms which are used to solve navigation problems in the Pacman world.
Friendly Environment for Neural Networks (fenn) is a simple Python framework for building ML/DL workflows and LLM agents faster, with prebuilt trainers, agent templates, logging, configuration management, and much more.
Long-term, cross-project memory for AI coding agents. Your own Obsidian vault as the source of truth. Daemonless and without opaque databases, your memory belongs to you.
Open standard for Provenance & Intent Contracts (PIC) in AI agents. Verify intent, provenance, and evidence before high-impact tool calls.
Agentic memory for CTI in Python — STIX knowledge graphs, threat-actor alias resolution, offline-first RAG, MCP server for Claude Code and LangChain agents
Dungeon Monkey Eternal- Third game in the dungeon monkey series, first written in Python.
Turn CSV, Excel, and read-only databases into verified, editable business reports.
Website to Scrapping all writeup from http://ctftime.org/ and you can organize which to read first!
Reverse ETL for the code-first data stack
Enterprise-grade platform to generate and execute Cypress, Playwright, WebdriverIO, and Appium end-to-end tests from natural language requirements. (Appium is experimental and requires external mobile infrastructure.)
A repo-native coding-agent loop harness for Claude, Codex, Copilot, and other CLI agents. Agents can edit. Gates decide what lands. You set the plan in motion. The agents take a prompt, and each iteration must update specs and commit through guardrails.
AlgoNim, the first Algorand game
High-fidelity transcript memory for Claude Code — index every session, recall byte-identical, search, prune, compose. Local-first, stdlib-only, MCP.
Conflict-free merge for DataFrames, JSON, ML models & distributed agents — powered by CRDTs. The first merge library where every operation is mathematically guaranteed to converge.
Stream-first CAN & J1939 toolkit for security research and AI agents — typed JSONL events, CLI, TUI, fuzzing, MCP server.
A Wagtail project starter template – with the solution to Wagtail’s official Your first Wagtail site tutorial.