Starred repositories
High-performance In-browser LLM Inference Engine
Lightpanda: the headless browser designed for AI and automation
Secure, Fast, and Extensible Sandbox runtime for AI agents.
High-performance browser automation bridge and multi-instance orchestrator with advanced stealth injection and real-time dashboard.
A high-performance, lightweight sandbox for running untrusted code securely on macOS Apple Silicon.
Parse partial JSON generated by LLM
Behavior trees for Unity3D projects. Written with a code driven approach on the builder pattern.
A python module to repair invalid JSON from LLMs
Production-ready platform for agentic workflow development.
Open-source observability for your GenAI or LLM application, based on OpenTelemetry
Langflow is a powerful tool for building and deploying AI-powered agents and workflows.
DSPy: The framework for programming—not prompting—language models
OpenTelemetry Instrumentation for AI Observability
The open-source LLMOps platform: prompt playground, prompt management, LLM evaluation, and LLM observability all in one place.
A lightweight, powerful framework for multi-agent workflows
Z80-μLM is a 2-bit quantized language model small enough to run on an 8-bit Z80 processor. Train conversational models in Python, export them as CP/M .COM binaries, and chat with your vintage compu…
Fastest enterprise AI gateway (50x faster than LiteLLM) with adaptive load balancer, cluster mode, guardrails, 1000+ models support & <100 µs overhead at 5k RPS.
Sandboxes for every agent. Embeddable, stateful, snapshots, and hardware isolation.
Pyodide is a Python distribution for the browser and Node.js based on WebAssembly
Python SDK, Proxy Server (AI Gateway) to call 100+ LLM APIs in OpenAI (or native) format, with cost tracking, guardrails, loadbalancing and logging. [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthr…
A C++20 library for fast serialization, deserialization and validation using reflection. Supports JSON, Avro, BSON, Cap'n Proto, CBOR, CSV, flexbuffers, msgpack, parquet, TOML, UBJSON, XML, YAML / …
Communicate with an LLM provider using a single interface
《Effective Modern C++》- 完成翻译
`std::execution`, the proposed C++ framework for asynchronous and parallel programming.
Location and syntax aware text objects which *do what you mean*
Fast, correct Python JSON library supporting dataclasses, datetimes, and numpy