llm-framework

A programming framework for agentic AI

Pocket Flow: Codebase to Tutorial

Pocket Flow: 100-line LLM framework. Let Agents build Agents!

Harness LLMs with Multi-Agent Programming

SRE Agent - CNCF Sandbox Project

No-code multi-agent framework to build LLM Agents, workflows and applications with your data

AICI: Prompts as (Wasm) Programs

ContextGem: Effortless LLM extraction from documents

[ICML 2024] LLMCompiler: An LLM Compiler for Parallel Function Calling

Official Repo for ICML 2024 paper "Executable Code Actions Elicit Better LLM Agents" by Xingyao Wang, Yangyi Chen, Lifan Yuan, Yizhe Zhang, Yunzhu Li, Hao Peng, Heng Ji.

Langtrace 🔍 is an open-source, Open Telemetry based end-to-end observability tool for LLM applications, providing real-time tracing, evaluations and metrics for popular LLMs, LLM frameworks, vectorDBs and more.. Integrate using Typescript, Python. 🚀💻📊

Virtualized Elastic KV Cache for Dynamic GPU Sharing and Beyond

The foundation layer for agentic intelligence.

🏆 Curated, ranked list of AI agent harnesses (100+) — plus an MCP server, llms.txt & JSON so agents can recommend them too. Rescored weekly.

The TypeScript framework for agents & workflows with react-like components. Lightning fast dev loop. Easy to learn. Easy to extend.

Design, conduct and analyze results of AI-powered surveys and experiments. Simulate social science and market research with large numbers of AI agents and LLMs.

Build, Improve Performance, and Productionize your AI Application

Super-Efficient RLHF Training of LLMs with Parameter Reallocation

FineTune LLMs in few lines of code (Text2Text, Text2Speech, Speech2Text)

Python library for building with LLMs. One interface across 11 providers (OpenAI, Anthropic, Gemini, DeepSeek, Ollama and more), automatic failover, Pydantic-validated structured output, embeddings with vector search, and an AI-powered router. pip install simplerllm