Explore the directory

An open cognitive architecture for a self-directed personal AI agent, combining persistent memory, self-directed learning and a graduated autonomy model with over 60 tools, meant to be cloned and run as one's own instance.

• Agent frameworks
• Agent memory

A Chinese-language tutorial project that teaches AI development on Spring Boot 3 and Spring AI by building a chat application and a ReAct-style autonomous planning agent called YuManus.

• Tutorials

An AI-powered, multi-agent security auditor for Symfony applications that runs an adversarial attacker-versus-reviewer loop to find application-level vulnerabilities that static analysis tools miss.

• Code quality
• Security

A small Go CLI that starts a local proxy so Claude Code and Codex CLI can run against an OpenCode Go subscription instead of their usual providers, in one command.

• LLM gateways
• CLI tools

A llama.cpp fork that adds sliding-window attention, multi-token prediction and a 4-bit KV cache to a Qwen hybrid model, keeping decode speed high at long context without losing long-range recall.

• Inference

An MCP server that gives coding agents a browser they can drive without CSS selectors, for debugging style issues, fixing console errors, mapping a web app's pages, and writing end-to-end tests.

• Testing
• Browser automation

A spec-driven, multi-agent harness for running a small software factory, where several AI agents work jobs in parallel from specifications, tracked on a Kanban board.

• Coding agents
• Agent frameworks

ROS 2 packages that bring whisper.cpp speech-to-text and Silero voice-activity detection into a robot's software stack, so a robot can listen for and transcribe speech.

• Speech

A local-first memory engine for AI agents that fuses vector, graph, and columnar storage under one query language, and can explain the evidence behind each recall.

• Agent memory
• Databases

An open-source extension stack for the Pi coding agent that adds language-server and Tree-sitter code intelligence, semantic refactoring, parallel code review, and structured ask-user forms.

• Coding agents
• Code quality

A composable, version-controlled prompt library that snaps together personas, reasoning protocols, output formats and templates into engineered prompts for tasks such as bug investigation and code review.

• Agent skills

A terminal AI coding agent that works with any LLM -- free local models through Ollama or cloud APIs -- with slash commands, checkpoints, hooks, agent roles and a headless mode for CI.

• Coding agents

An open-source harness that turns OpenCode into a structured team of specialized agents for research, design, specification, implementation, review and validation, with durable state and explicit handoffs.

• Coding agents
• Agent frameworks

A step-by-step, chapter-based tutorial that builds an AI coding agent from scratch in TypeScript, covering the agent loop, tools, file editing, context, permissions, subagents and streaming.

• Tutorials

A command-line tool that opens a web page in a real browser, works out a test plan purely mechanically from the controls it finds, drives them, and reports exactly which control broke and how.

• Testing
• Browser automation

A self-paced, sixteen-week course that takes a learner from a first Windows Server logon through building, attacking and hardening a full enterprise Windows environment on a lab domain.

• Security
• Tutorials

A tool that hooks into tmux-resurrect to save and relaunch AI coding assistant sessions, such as Claude Code, Cursor Agent CLI, GitHub Copilot CLI, OpenCode, Codex CLI and Pi, after a tmux restart or reboot.

• Coding agents
• Terminals

An externally scored benchmark for machine-learning research agents, with 60 tasks across tabular, forecasting, vision, language, audio and scientific data, and a protocol that keeps holdout labels away from the agent under test.

• AI evals

A guide to running large language models on local hardware using frameworks such as llama.cpp, Ollama, Hugging Face Transformers, vLLM and LM Studio, with setup steps and performance notes.

• Tutorials

A command-line tool that captures the reasoning behind an AI coding session at every git commit and stores it in the repository, so any coding agent can recall why a past decision was made.

• Agent memory
• Git

A hands-on workshop that teaches how to build AI-infused applications with Quarkus and LangChain4j, covering both single AI service calls and agentic orchestration.

• Tutorials

A Rust and WebAssembly runtime that runs Cactus Compute's Needle tool-calling models in a browser tab, Cloudflare Workers, Node.js, Python, C FFI or embedded no_std targets, with no server or API key.

• Inference

A from-scratch C inference engine that runs a 45-million-parameter tool-calling language model entirely on a five-dollar ESP32-S3 microcontroller, with no Linux, Python or network connection.

• Inference

A Python toolkit for composing pretrained LoRA adapter functions into one deployable model, so capabilities such as RAG, safety and factuality can be combined, swapped or upgraded like software libraries.

• Models