AI Agents & LLM Frameworks Telemetry Index

Local execution runtime and model manager for running large language models on developer hardware.

Context-aware reasoning framework for building composable LLM applications and autonomous agents.

Self-hosted extensible AI interface supporting Ollama, OpenAI-compatible APIs, and local RAG.

Open-source LLM app development platform combining agentic workflows, RAG pipelines, and observability.

LLM inference in C/C++ with minimal setup and hardware acceleration across CPU, Metal, and CUDA.

Autonomous AI software engineering agents capable of executing terminal commands, editing code, and browsing.

High-throughput and memory-efficient inference and serving engine for Large Language Models.

Programming framework for agentic AI and multi-agent conversational systems.

Framework for orchestrating role-playing, autonomous AI agents in collaborative workflows.

Lightweight terminal coding agent that runs locally and executes repository tasks safely.

Agentic terminal coding tool that understands codebases and executes engineering workflows.

The AI Toolkit for TypeScript: unified streaming, tool calling, and agent primitives for web stacks.

Resilient, stateful multi-actor agent orchestration library built on graph state machines.

Type-safe Python agent framework designed for production generative AI workflows by the Pydantic team.