Catalogue
Frameworks
Harnesses, frameworks, tools, apps, and platforms for agent builders, each scored on real GitHub credibility and each with a credibility-gated forum.
55 tools · showing 1–24
FrameworkLiveKit Agents
Voice
livekit
Framework for building realtime, server-side voice agents with pluggable STT, LLM, and TTS and WebRTC/telephony support
webrtctelephonyreal-timestt
FrameworkDify
Coding
langgenius
Open-source LLM app development platform combining a visual workflow canvas, RAG pipelines, agents, model management, and observability
productivityragagent-builderorchestrationobservability
FrameworkCrewAI
Coding
crewAIInc
Python multi-agent framework pairing autonomous role-based Crews with event-driven Flows for precise orchestration
multi-agentorchestration
FrameworkLangChain
CodingMemory
langchain-ai
Framework for building LLM applications and agents from interoperable components and a large integrations library
ragmulti-agentorchestrationtool-calling
FrameworkAgno
CodingDeployment
agno-agi
SDK, AgentOS runtime, and web UI for building and operating multi-tenant agent platforms on your own infrastructure
authobservabilitycroncontrol-plane
FrameworkAI SDK
CodingInterface
vercel
TypeScript toolkit for LLM calls, tool use and multi-step agent loops.
streamingtool-callinggenerative-uimulti-provider
FrameworkMicrosoft Agent Framework
Coding
microsoft
Successor SDK merging AutoGen and Semantic Kernel into one agent-building library.
multi-agentorchestrationautogensemantic-kernel
FrameworkSemantic Kernel
Coding
microsoft
SDK that composes LLM prompts, plugins and planners into agents in C#/Python/Java.
orchestrationmulti-agentpluginplanner
FrameworkBeeAI
Coding
i-am-bee
Python and TypeScript framework for multi-agent systems with ACP/A2A and MCP integrations and composable workflows
multi-agentacpa2aworkflow-composition
FrameworkCAMEL
CodingData Wrangling
camel-ai
Multi-agent framework for role-playing agents, large-scale society simulation, and synthetic data generation
multi-agentrole-playingsynthetic-datasimulation
FrameworkEmbabel Agent
Coding
embabel
Embabel (Em-BAY-bel) is a framework for authoring agentic flows on the JVM that seamlessly mix LLM-prompted interactions with code and domain models.
springgoal-oriented-planningmulti-agentorchestration
FrameworkHaystack
Coding
deepset-ai
Open-source Python framework for building production LLM pipelines for RAG, search, and agents
ragsemantic-searchorchestrationdeepset
FrameworkMastra
CodingMemoryQA
mastra-ai
TypeScript framework for AI agents and apps, with model routing, graph-based workflows, memory, and built-in evals
orchestrationragnextjs
FrameworkNeMo Agent Toolkit
CodingMonitoringQA
NVIDIA
Library for connecting, profiling and optimizing teams of agents across frameworks.
profilingobservabilityevaluationmulti-agent
FrameworkOpenAI Agents SDK
CodingVoiceSecurity
openai
Python framework for multi-agent workflows with handoffs, guardrails, sessions, sandbox and voice agents, and built-in tracing
multi-agentguardrailsobservabilitysandbox
FrameworkStrands Agents
Coding
strands-agents
Model-driven Python SDK for building agents with tools in a few lines.
sdkmulti-agenttool-callingcloud
FrameworkTrigger.dev
CodingDeployment
triggerdotdev
Open-source TypeScript platform for long-running, durable agent and workflow tasks with retries, queues and replay.
orchestrationdurable-executioncronsdk
FrameworkAgent Development Kit (ADK)
CodingQADeployment
Google's open-source SDK for building, evaluating and deploying multi-agent systems.
multi-agentadk-webevaluation
FrameworkDeep Agents
CodingMemory
langchain-ai
Opinionated, model-agnostic agent harness on LangGraph with sub-agents, filesystem, and context management built in
langchainmulti-agenttoken-optimizationhuman-in-the-loop
FrameworkCopilot SDK
Coding
github
Multi-platform SDK for integrating GitHub Copilot Agent into apps and services
sdkcoding-agentembeddable
FrameworkDSPy
CodingTraining
stanfordnlp
Compose LM pipelines as declarative Python modules, then optimize their prompts and weights algorithmically
promptragself-improvement
FrameworkPydantic AI
Coding
pydantic
Python agent framework from the Pydantic team for building type-safe, model-agnostic generative-AI applications and workflows
pydantictype-safemulti-providerstructured-output
FrameworkVerifiers
Monitoring
PrimeIntellect-ai
Library of shareable RL environments and rubric-based verifiers for agents.
reinforcement-learningevaluation
FrameworkMetaflow
DeploymentCoding
Netflix
Human-centric framework designed to help scientists and engineers build and manage real-life AI and ML systems.
mlopsorchestrationkubernetesexperiment-tracking