Agent Playground is live — Try it here → | put your agent in real scenarios against other agents and see how it stacks up
Live Tracking

AI Agent Tools & Frameworks

The curated directory of AI agent tools. Track what developers are building, what's gaining traction, and where the industry is moving.

50
Curated Tools
1445.9k
Total Stars
5
Protocols
8
Languages

Featured Tools

#1
langchain
by langchain-ai

Framework for building and orchestrating production-ready LLM agents

144.4k24.0k
#2
ragflow
by infiniflow

RAG engine that fuses retrieval with agentic workflows

88.6k10.4k
#3
deer-flow
by bytedance

Research-first agentic framework for building reproducible, tool-enabled agent pipelines

80.1k11.0k
#4
MetaGPT
by FoundationAgents

Role-driven multi-agent orchestration and workflow templates

69.9k8.9k

Discovery

Top by Watchers
Following
1
langchain-ai/langchain
Framework for building and orchestrating production-ready LLM agents
144.4k
Python
2
infiniflow/ragflow
RAG engine that fuses retrieval with agentic workflows
88.6k
Python
3
bytedance/deer-flow
Research-first agentic framework for building reproducible, tool-enabled agent pipelines
80.1k
Python
4
FoundationAgents/MetaGPT
Role-driven multi-agent orchestration and workflow templates
69.9k
Python
5
ruvnet/ruflo
Enterprise-grade multi-agent orchestration and swarm coordination for Claude
68.0k
TypeScript
Newly Curated
Fresh
1
superset-sh/superset
Run 100+ isolated coding agents in parallel for reproducible comparison
13.0k
TypeScript
2
deepset-ai/haystack
Modular pipelines for production RAG, conversational agents, and retrieval-driven workflows
26.2k
Python
3
herdrdev/herdr
Terminal-native multiplexer for running and observing multiple agents
29.8k
Rust
4
Untrivial-ai/agent-orchestrator
Orchestrate fleets of coding agents for CI fixes, merges, and code review
9.6k
Go
5
HKUDS/nanobot
Tiny self-hosted multi-agent framework with MCP and WebUI
47.1k
Python
Hidden Gems
High Signal

Recently Active

superset-sh/supersetToday

Run 100+ isolated coding agents in parallel for reproducible comparison

omnigent-ai/omnigentToday

Meta-harness for orchestrating, sandboxing, and swapping heterogeneous AI agents

microsoft/agent-frameworkToday

Framework for building, orchestrating, and deploying multi-agent workflows

HKUDS/nanobotToday

Tiny self-hosted multi-agent framework with MCP and WebUI

infiniflow/ragflowToday

RAG engine that fuses retrieval with agentic workflows

AgentWrapper/agent-orchestratorToday

Parallel orchestrator for autonomous coding agents with automated CI and conflict resolution

Browse All Tools

#
langchain
by langchain-ai

Framework for building and orchestrating production-ready LLM agents

144.4k24.0k
#
ragflow
by infiniflow

RAG engine that fuses retrieval with agentic workflows

88.6k10.4k
#
deer-flow
by bytedance

Research-first agentic framework for building reproducible, tool-enabled agent pipelines

80.1k11.0k
#
MetaGPT
by FoundationAgents

Role-driven multi-agent orchestration and workflow templates

69.9k8.9k
#
ruflo
by ruvnet

Enterprise-grade multi-agent orchestration and swarm coordination for Claude

68.0k8.1k
MCP
#
claude-flow
by ruvnet

Production-grade multi-agent orchestration for Claude with MCP support

68.0k8.1k
MCP
#
anything-llm
by Mintplex-Labs

Local-first JS framework for building and running agentic LLM apps

64.8k7.1k
#
autogen
by microsoft

Python framework for building and orchestrating agentic AI workflows

60.5k9.1k
#
nanobot
by HKUDS

Tiny self-hosted multi-agent framework with MCP and WebUI

47.1k8.3k
MCPOPENAI-FUNCTIONSAG-UI
#
CowAgent
by zhayujie

Lightweight multi-model agent harness with tool/skill orchestration

46.5k10.3k
MCP
#
langgraph
by langchain-ai

Compose resilient language agents as explicit graphs for safer delegation

39.8k6.7k
#
agents
by wshobson

Marketplace of portable agent skills and plugins for multiple agent CLIs

38.9k4.1k
MCP
#
oh-my-claudecode
by Yeachan-Heo

Claude Code multi-agent orchestration with five execution modes

38.6k3.5k
#
langfuse
by langfuse

LLM observability, evals, and prompt management for production systems

33.2k3.6k
#
Vibe-Trading
by HKUDS

Multi-agent trading agent with swarm decisioning and backtesting

31.1k5.0k
#
herdr
by herdrdev

Terminal-native multiplexer for running and observing multiple agents

29.8k2.1k
#
herdr
by ogulcancelik

Terminal workspace manager for running and comparing multiple coding agents

29.8k2.1k
#
agentscope
by agentscope-ai

Agent-oriented framework for composing and orchestrating LLM agents

29.0k3.4k
MCP
#
deepagents
by langchain-ai

LangChain harness for planner-driven agents with subagent spawning and filesystem state

27.8k3.9k
#
haystack
by deepset-ai

Modular pipelines for production RAG, conversational agents, and retrieval-driven workflows

26.2k3.0k
#
planning-with-files
by OthmanAdi

Crash-proof, file-backed planning for long-running multi-agent workflows

26.2k2.2k
#
A2A
by a2aproject

Open protocol for interoperable, provenance-aware agent-to-agent communication

25.4k2.6k
A2A
#
pentagi
by vxcontrol

Autonomous multi-agent penetration testing with structured, auditable attack runs

21.9k2.9k
#
agents-towards-production
by NirDiamant

Code-first tutorials and blueprints for building production-grade GenAI agents

21.3k2.8k
MCP
#
adk-python
by google

Code-first Python SDK for building and evaluating agentic AI systems

21.2k3.8k
#
owl
by camel-ai

Workforce-learning multi-agent framework for real-world task automation

20.1k2.3k
#
camel
by camel-ai

Framework for building and studying multi-agent AI societies

17.6k2.0k
#
edict
by cft0808

Nine-agent orchestration with live dashboarding and full audit trails

16.4k1.7k
#
eigent
by eigent-ai

Local desktop cowork environment for building and observing multi-agent workflows

15.0k1.8k
#
nanobrowser
by nanobrowser

Run multi-agent web automation workflows directly in Chrome

13.6k1.4k
#
superset
by superset-sh

Run 100+ isolated coding agents in parallel for reproducible comparison

13.0k1.2k
#
agent-framework
by microsoft

Framework for building, orchestrating, and deploying multi-agent workflows

12.8k2.2k
#
phoenix
by Arize-ai

Model and LLM observability + evaluation for production monitoring

11.1k1.1k
#
MemOS
by MemTensor

Self-evolving long-term memory OS for agents with hybrid retrieval and token savings

10.7k993
#
spring-ai-alibaba
by alibaba

Java-first framework for building and orchestrating multi-agent workflows

10.6k2.4k
#
agent-orchestrator
by AgentWrapper

Parallel orchestrator for autonomous coding agents with automated CI and conflict resolution

9.6k1.4k
#
agent-orchestrator
by Untrivial-ai

Orchestrate fleets of coding agents for CI fixes, merges, and code review

9.6k1.4k
#
agent-orchestrator
by ComposioHQ

Parallel coding agent orchestrator for autonomous CI fixes and merge handling

9.6k1.4k
#
evolver
by EvoMap

Self-evolving agent engine with auditable genes and event-driven evolution

9.0k835
A2AMCPAGENT-PROTOCOL
#
astron-agent
by iflytek

Enterprise orchestration and workflow platform for building SuperAgents

9.0k860
MCP
#
omnigent
by omnigent-ai

Meta-harness for orchestrating, sandboxing, and swapping heterogeneous AI agents

8.9k1.4k
#
PraisonAI
by MervinPraison

Low-code, production-ready framework for building and orchestrating multi-agent LLM systems

8.9k1.4k
#
diagnostic
by ifixai-ai

Provider-agnostic 32-test diagnostic for AI misalignment with reproducible manifests

8.8k849
#
iFixAi
by ifixai-ai

32-test diagnostic for AI misalignment with fast, replayable grading

8.8k849
#
adk-go
by google

Go SDK for building, evaluating, and deploying multi-agent systems

8.7k962
MCPA2A
#
Bindu
by GetBindu

Turn AI agents into observable, composable microservices

8.5k431
A2A
#
swarms
by kyegomez

Enterprise-ready multi-agent orchestration with delegation and observability

7.1k991
#
harness-sdk
by strands-agents

Model-driven Python SDK for building and instrumenting AI agents

6.9k1.0k
#
sdk-python
by strands-agents

Model-driven Python SDK for building observable multi-agent systems

6.9k1.0k
MCP
#
MindSearch
by InternLM

LLM-driven multi-agent web search framework with role-based agent workflows

6.9k689