Report Abuse

Basic Information

This repository is an organized, community-maintained index of open-source AI agents and related resources focused on LLM-driven autonomous and multi-agent systems. It catalogs projects, frameworks, benchmarks, platforms, research surveys, paper lists and blogs that explore autonomous task solvers, multi-agent collaboration, agent society simulation and advanced agent components like memory layers and tool APIs. The README groups entries into clear sections such as Applications, Frameworks, Benchmark/Evaluator, Platforms/API, Related and Reference Repos, and lists representative projects and frameworks for each category. The collection is intended as a discovery and reference hub for people interested in the ecosystem of LLM-based agents and the tools, evaluations and literature that support them.

Links

Categorization

App Details

Features
Categorized curation across multiple sections including Autonomous Agent Task Solvers, Multi-Agent Task Solvers, Agent Society Simulation, Advanced Components, Frameworks, Benchmarks and Platforms. Each entry names prominent open-source projects and frameworks and links to their repositories and badges. The README highlights example projects and frameworks for quick reference, shows visual diagrams and images for some sections, and aggregates surveys, paper lists and blog posts to connect research and practical tooling. It also collects benchmark and evaluation tools, monitoring and observability projects, and reference repositories to support further exploration and comparison of agentic approaches.
Use Cases
The repo helps researchers, engineers and enthusiasts quickly find and compare open-source agent projects, frameworks, benchmarks and platform integrations in one place. It reduces discovery time by grouping projects by purpose and maturity, offering examples of autonomous and multi-agent systems, simulation projects, memory and tooling components, and evaluation suites. Users can follow links to individual repositories to evaluate capabilities, adopt frameworks, run benchmarks, read surveys and follow paper lists and blogs for background. The resource supports exploration of practical and research directions in building, evaluating and deploying LLM-powered agents and agent societies.

Please fill the required fields*