MCP Client2025
Official Go implementation of the Model Context Protocol for building MCP servers and clients. Tool handlers are type-safe, with JSON schemas inferred from Go structs via generics. Ships stdio, command, streamable-HTTP, SSE, and in-memory transports.
AI Image2025
Converts document images—scans, photos, born-digital PDFs—into structured text in two stages: first map layout and reading order, then parse each element (text, tables, formulas, figures) in parallel, each guided by its own task prompt.
AI Infra2025
Reimplements the vLLM inference engine from scratch in ~1,200 lines of readable Python, matching its offline throughput on small models. Prefix caching, tensor parallelism, torch.compile, and CUDA graphs are all kept legible.
AI Agent2025
Unifies agentic tasks, reasoning, and coding in a single MoE model with 355B total / 32B active parameters and a switchable thinking mode. A lighter 106B-param Air variant trades scale for efficiency; both ship MIT-licensed.
AI Infra2025
An open-source memory layer that turns agent runs and conversations into structured, persistent state recallable across sessions. Captures facts, events, preferences, and relationships automatically; LLM-agnostic with SDK and MCP integration.
AI Agent2025
A TypeScript agent harness split into composable npm packages: a unified LLM API across OpenAI, Anthropic and Google, an agent runtime with tool calling and state, a self-extensible coding-agent CLI, and a differential-rendering terminal UI library.
AI Deploy2025
Turns OpenAI Whisper into a live streaming transcriber: audio flows in over WebSocket and text returns word-by-word instead of after full utterances. Adds SimulStreaming and LocalAgreement decoding, Silero VAD, and speaker diarization, all self-hosted.
AI Deploy2025
A ~5,000-line Python LLM inference engine that re-implements SGLang's serving optimizations — radix KV-cache reuse, chunked prefill, overlap scheduling, tensor parallelism — as a fully type-annotated reference instead of a black box.
AI Infra2025
Extends vLLM beyond text to serve omni-modal models — Qwen3-Omni, TTS like CosyVoice3, and diffusion image/video/audio generators — in one engine, adding the non-autoregressive Diffusion Transformer support the core project never targeted.
AI Audio2025
Delivers multilingual, on-device text-to-speech via ONNX Runtime with prebuilt ONNX assets and cross-platform SDKs (Python, Node, mobile); targets low-latency, privacy-preserving TTS with ready demos and 31-language support in v3.
MCP Server2025
Official MCP server for data.gouv.fr, France's national open-data portal: lets chatbots search datasets, query CSV/XLS via the Tabular API, and browse cataloged third-party APIs, all read-only over a public HTTP endpoint that needs no key.
AI Infra2025
Embeds into an app like SQLite, persisting to a local file with no server or separate process. Combines dense and sparse vectors, full-text search, and scalar filters in one hybrid query; C++ core with Python, Node, Go, Rust, and Dart bindings.