Explore the directory

A production-grade AI agent framework for Elixir and the BEAM, running agents as supervised OTP processes with crash recovery and switching between 13 LLM providers by changing one string.

• Agent frameworks

A local memory tool for coding agents that indexes shell command history with exit codes, git commit history down to the diff, and project docs into a local SQLite database, then serves back a ranked, token-budgeted slice on demand.

• Agent memory

A post-training quantization method, presented at ICML 2026, that compresses large language model weights below one bit per parameter using mixture-of-rank binary bases while preserving accuracy.

• Models
• Papers

An offline-first interactive lab and long-form guide to Muse Glimmer, Meta's open-weight 30-billion-parameter agentic multimodal model, letting a reader explore agent loops, benchmarks, and memory sizing before downloading the model weights.

• Models
• Tutorials

The course hub for a university-style class on multi-agent systems and agentic AI, holding lecture slides, code, tutorials, and reading materials covering reinforcement learning and multi-agent reinforcement learning.

• Tutorials

An open-source, multi-protocol mock server for HTTP, GraphQL, SOAP, and gRPC, with weighted traffic splitting, dynamic JavaScript responses, chaos-testing fault injection, and an MCP server so an AI assistant can generate mock rules directly.

• Testing
• APIs

A markdown-first, long-term memory tool for AI coding agents that indexes your notes, documents, and code with hybrid keyword and semantic search, exposed to any agent through MCP.

• MCP servers
• Agent memory

A mechanistic interpretability study tracking whether the induction-head circuit in a small attention-only transformer survives fine-tuning from prose to structured Python code, using per-head induction scores and activation patching across training checkpoints.

• Papers

A hands-on lab repository that teaches the Model Context Protocol through guided exercises in a GitHub Codespace, kept current with the MCP specification and built on FastMCP 4.

• Tutorials

The official source code accompanying the Apress book Mastering Retrieval-Augmented Generation by Ranajoy Bose.

• RAG
• Books

A downloadable, self-hosted AI agent framework that works immediately after installing, with a modular system of personalities, connectors, and providers that can be reconfigured without writing code.

• Agent frameworks

A self-hostable agentic runtime that runs as one Go binary alongside your application, handling the agent loop, multi-provider LLM routing, memory, and MCP on both sides, reachable over HTTP, gRPC, MCP, or TypeScript/Python adapters.

• Agent frameworks

An AI development orchestration tool that spawns coding agents to claim GitHub or Gitea issues, implement features, review pull requests, and merge code, coordinated entirely through issue and PR labels.

• Coding agents
• Git

A SwiftUI showcase chat app demonstrating Apple's on-device Foundation Models on iOS 26 and iOS 27, providing fast, private AI chat with no app server and no data leaving the device.

• Inference
• Tutorials

A benchmarking tool that sweeps llama.cpp settings on your own GPU or CPU to find the fastest configuration for a given model, and compares the result against a shared database of other people's hardware and settings.

• Inference
• Testing

A fast Rust command-line tool that pulls in data from local files, git repositories, websites, Hugging Face datasets, and file hosts, cleans and classifies it, and builds deduplicated, leakage-safe chat-format JSONL datasets for training and retrieval.

• RAG
• Data engineering

A policy-and-trust layer that turns declarative YAML configs into Model Context Protocol tool servers with trust-tier enforcement, credential brokering, and tamper-evident audit logging built in.

• MCP servers
• Security

An MCP server that gives AI coding assistants long-term, on-device memory inside an IDE, backed by the Kuzu graph database with semantic vector search, and integrated with VS Code, Cursor, and Windsurf.

• MCP servers
• Agent memory

An Expo module that wraps Apple's on-device Foundation Models on iOS and Google's Gemini Nano through ML Kit on Android behind one on-device LLM inference API for React Native apps.

• Inference
• Mobile

A full-duplex voice plugin for DeepSeek Harness that streams speech recognition into an editable draft as you talk, reads replies aloud sentence by sentence with live captions, and lets you interrupt playback just by speaking.

• Agent skills
• Speech

A plugin for DeepSeek Harness that turns local Markdown and text files into a queryable knowledge base, with hybrid semantic and keyword search, diversity re-ranking, and citation checking the agent can verify.

• Agent skills
• RAG

A bridge that lets Claude Cowork or Claude in the browser hand a task to a real Claude Code agent running on the user's own Mac, Linux, or WSL2 machine, streaming the result back to the chat.

• Coding agents

An interactive Jupyter notebook curriculum for learning artificial intelligence by implementing it, moving from search and constraint algorithms through formal reasoning, game theory, machine learning, reinforcement learning, and generative AI to algorithmic trading.

• Tutorials

An MCP server that lets AI agents search, compare, and track prices across more than 300 million products from US, Singapore, and Southeast Asian merchants such as Lazada, Shopee, and Amazon.

• MCP servers
• APIs