Explore the directory

A polyglot binding generator that reads a Rust library's public API and emits fully typed, native bindings, package scaffolding, documentation and end-to-end tests for 16 other languages.

• CLI tools
• Libraries

The source repository for Milvus's technical documentation, covering the open-source vector database's releases from 1.0.0 through its current branch.

• Databases
• Documentation tools

Research code for a two-stage reinforcement fine-tuning method that trains large language models to reason step by step about time series data before producing a forecast.

• Models
• Papers

An open-source, self-hostable retrieval-augmented-generation platform that ingests documents, embeds and indexes them with Turbopuffer, and serves semantic, keyword and hybrid search behind one REST API.

• RAG
• Databases

A library of Megatron-Core model definitions for large and multimodal models, letting a developer train models such as Qwen3-Next, GLM-5, DeepSeek-V4 and MiniMax with Megatron-Core's parallelism techniques as easily as with Transformers.

• Models
• Libraries

A distributed micro-language-model system that splits a 56 million parameter model across three ESP32-S3 microcontrollers connected over ESP-NOW, with a browser interface for typing prompts and streaming generated text.

• Models
• Inference

A multi-agent, self-correcting retrieval-augmented reasoning engine that plans multi-hop evidence retrieval, then has a critic and reviser iterate on an answer until it converges, with reproducible evaluation against a judge.

• Agent frameworks
• RAG

A CLI that turns a repository into a self-organizing AI engineering team of eight specialist agents, running a contract-driven, evidence-gated loop of dispatch, build, test and review until a pull request lands.

• Coding agents
• Agent frameworks

A schema-driven code generator, built by Grafana, that reads CUE, JSON Schema or OpenAPI definitions and emits typed classes and builder libraries in Go, Java, PHP, Python or TypeScript.

• Libraries
• APIs

An embedded, multimodal vector database built for local retrieval-augmented generation, positioned as a drop-in, GPU-accelerated backend for frameworks such as LangChain, LlamaIndex, and mem0.

• RAG
• Databases

A prompt-injection firewall for MCP that scans every tool response through four layers of detection before an agent reads it, wrapping any MCP server with no configuration change to the agent.

• MCP servers
• AI evals

An adaptive local-inference provider for the Hermes Agent chat bot that inventories a machine's compute and memory, recommends the best model it can safely run, and exposes it through one OpenAI-compatible endpoint.

• Inference

A framework for deploying, testing and evaluating pretrained autonomous-driving agents from the CARLA Leaderboard on a vehicle in the CARLA simulator, decoupled from the Leaderboard's own codebase.

• Testing

An SDK for building agentic MCP servers by composing and fine-tuning existing Model Context Protocol tools, wrapping them into new tools, multi-agent systems, or code-execution and sandboxed sampling modes.

• Agent frameworks
• MCP servers

A lightweight command-line and GUI tool, written in Zig, that converts safetensors model files into various GGUF quantizations, targeting image and video diffusion model architectures.

• Models
• CLI tools

A local governance daemon for AI agents that enforces declarative tool-call policies deterministically before each call runs, with identity-bound credentials and a tamper-evident audit log.

• AI evals
• Security

A self-hosted AI workspace that turns a plain-English chat request into an editable visual workflow, with a planner, implementer and independent reviewer completing an acceptance contract before any side effect runs.

• Agent frameworks
• Workflow automation

A platform for semantic search across large video datasets, supporting text-to-video and video-to-video queries with GPU-accelerated embeddings and vector similarity search.

• RAG
• Databases

A cross-language code-intelligence engine that builds a semantic graph of a codebase's functions, classes, imports and call chains, exposed through MCP tools, a VS Code extension, a JetBrains plugin and a persistent memory layer.

• MCP servers
• Agent memory

A GitHub Actions bot that reviews pull requests with the Claude API, posting inline comments on changed lines and a summary comment on every pull request.

• Code quality
• CI/CD

A Helm chart that deploys a complete LLM operations stack on Kubernetes in one command, covering model serving, a unified API gateway, observability, autoscaling and fine-tuning.

• Inference
• Containers
• Monitoring

A durable, file-based long-term memory system for AI agents distributed as five packages, an SDK, a CLI, an MCP server, a Hermes adapter and a LangGraph store, with no vector database and no embeddings.

• Agent memory

A distributed implementation of llama.cpp that spreads a 30 to 70 billion parameter model's layers across ordinary home devices, such as laptops, desktops, phones and tablets, keeping memory pressure low without requiring a GPU on every device.

• Inference

An API layer in front of the Ollama API that adds tools from multiple Model Context Protocol servers so every Ollama chat request can call them, while every other Ollama endpoint is proxied through unchanged.

• MCP servers
• Inference