Framework
217 tools across 4 categories tagged with “framework”
frameworks
(121)FastMCP
The fast, Pythonic way to build MCP servers — 24K+ stars
ActiveGraph
Event-sourced graph runtime with time-travel debugging for auditable agent systems
AdMem
Multi-level memory framework enabling agents to learn from past tasks, failures, and procedures
Agency Swarm
Open-source framework for orchestrating role-based AI agent swarms with Python
agentdev
Lightweight AI agent framework with built-in debugger for OpenAI, Anthropic & MCP
AgentFlyer
Decentralized multi-host AI agent framework with cross-platform federation
AgenticCyOps
Enterprise security framework for multi-agent AI in cyber operations
AgenticRec
Agentic framework for optimizing recommendation system rankings through end-to-end policy learning
Aiframe Agent CLI
Enterprise-grade AI agent framework with workflow orchestration and production reliability
AOHP
OS-level harness for secure and efficient AI agent execution with native system integration
Ares
Adaptive reasoning framework that optimizes LLM inference costs by dynamically scaling effort
@astrive-ai/sdk
Universal JavaScript/TypeScript AI agent framework with multi-provider function calling
AsyncFC
Asynchronous function calling framework that parallelizes LLM tool execution for faster agents
AutoAgent
Self-evolving multi-agent framework with adaptive cognition and elastic memory for open-ended tasks
AutoAgent
Self-evolving multi-agent framework with adaptive learning and elastic memory orchestration
Automat
Autonomous feature engineering for materials science via LLM-driven genetic programming
BrainAgent
Multi-agent framework for autonomous brain signal analysis and BCI development
BrainOS JS
High-performance multi-agent framework with Rust core and Node.js bindings
BrainOS
High-performance multi-language AI agent framework powered by Rust with Node.js bindings
BrainOS (JSBOS)
High-performance multi-language agent framework bridging Node.js and Rust
BrainOS
Multi-language agent framework with Rust core, event bus, and MCP support
BrowserDD
Production-grade LLM-powered browser automation framework with DOM analysis and multi-model support
CAST
Case-driven framework that learns from execution trajectories to optimize LLM tool use
CAST (CausalSteward)
Human-in-the-loop framework for causal discovery using LLM agents and divide-conquer strategies
Chiron
Industrial platform coordinating humans and AI agents across software delivery lifecycle
Cipher
Memory-powered AI agent framework with WebSocket communication and MCP integration
Cray Code
Claude-native agent framework with MCP, skills, and hierarchical sub-agents
DeepCLAW
Enterprise AI agent framework with zero-trust security and hardware-backed governance controls
Easy Agent Core
Lightweight AI agent framework with session orchestration and MCP support
EchoGuard
Knowledge Graph-powered memory framework for detecting manipulation in long-term AI conversations
ELITE
Self-improving embodied AI framework that learns from mistakes and transfers knowledge across tasks
EnterpriseLab
Enterprise-grade framework for privacy-preserving AI agent development with closed-loop training
Ethos Agent Framework
TypeScript framework where AI agent personality shapes architecture and behavior
Ethos Agent
TypeScript framework for building AI agents with personality-driven architecture and identity
Ethos
TypeScript framework where agent personality drives architecture and behavior
EvoTool
Evolutionary framework that self-optimizes tool-use policies for long-horizon LLM agent tasks
Fal Agent
Type-safe AI agent framework with declarative routing and provider abstraction
FastMCP
Fast, Pythonic framework for building Model Context Protocol servers and clients
fastmcp
Pythonic framework for building MCP servers and clients with minimal boilerplate
Flama
ASGI framework unifying REST APIs, ML serving, and LLM apps in production-ready Python
Fred AI
Type-safe AI agent framework built on Effect-TS with functional programming patterns
Fred AI
Effect-based TypeScript framework for type-safe, composable AI agents
Glite ARF
Verifier-driven framework for parallel LLM coding agents with built-in audit capabilities
GLM-5.2
Open-source MoE language model optimized for conversational AI and agentic workflows
HarnessX
Composable runtime scaffolding for adaptive AI agents that learn from execution traces
Helix Agent Framework
Privacy-focused, offline-capable AI agent framework for JavaScript/TypeScript
HiMAP-Travel
Hierarchical multi-agent framework for long-horizon constrained planning with resource allocation
HyperTool
Execute multi-step workflows as single tool calls to reduce agent overhead
IQAI ADK
TypeScript-native framework for production AI agents with multi-provider LLM orchestration
IronEngine
Unified orchestration platform with multi-phase planning, 24-category tools, and adaptive model switching
Jarvis Agent
Production-ready JavaScript framework for browser automation and AI workflow agents
jsbos
Multi-language AI agent framework for Node.js with Rust-powered performance
Kernl
Modern TypeScript framework for production-grade AI agents with native MCP support
Kernl
Modern AI agent framework with native Model Context Protocol integration
Kernl
Modern AI agent framework with native MCP support for streamlined development
Kernova Framework
Full-stack AI agent framework unifying React/Next.js frontend with integrated agent orchestration
Kognitive Agents
Open-source AI agent framework with built-in safety guardrails and multi-agent coordination
Laguna-M.1
MoE-based conversational AI framework optimized for efficient code generation and agent workflows
Lakitu
Self-hosted AI agent framework with real-time database and sandboxed code execution
Lakitu
Self-hosted AI agent framework combining Convex real-time sync with E2B sandboxed execution
Learn Claude Code
Learn to build Claude Code-like agents from scratch with hands-on tutorials
LLM-Wiki
Agent-native retrieval system using Retrieval-as-Reasoning for dynamic knowledge navigation
LOGOS
Self-evolving governance layer for AI agent teams with human-in-the-loop oversight
Looopy AI Core
Reactive AI agent framework built on RxJS for event-driven, composable agent architectures
Looopy AI
RxJS-powered reactive AI agent framework with functional programming patterns
Looopy AI
Reactive AI agent framework built on RxJS for observable-driven agent patterns
MADA
Multi-agent framework for HPC-powered design workflows with automated experiment tracking
Maiar AI
Plugin-based AI agent framework for building modular, extensible agent systems
Mana
Sim-to-real framework treating robotic manipulation as animation for dexterous tasks
MANTA
Dynamic multi-agent network topology adaptation framework for self-evolving collaboration
MARC Framework
Clinical AI framework with deterministic multi-agent orchestration and role-specialized reasoning
Mayros
Multi-channel AI framework with knowledge graph integration and MCP support
Motif-3
MoE-based long-context agent framework with formal verification and multilingual support
NanoBot
Ultra-lightweight self-hosted AI agent framework with 46k+ stars
NVIDIA OO Agents
Object-oriented Python framework for building AI agents with native code patterns
OpenForgeRL
End-to-end RL training framework for stateful, multi-process agent harnesses
OpenForgeRL
End-to-end RL framework for training stateful coding agents across diverse environments
Orchard
Microsoft's framework for training autonomous agents with planning, reasoning, and tool use
PMAx
Natural language interface for AI-driven process mining and workflow analysis
Pydantic AI
Type-safe Python agent framework built on Pydantic's validation system
QUARE
Multi-agent framework for resolving quality attribute conflicts in requirements engineering
Quasar
18B parameter MoE foundation model optimized for long-context agent applications
Quasar
10B parameter foundation model with 2M token context using Gated Linear Attention
Quoroom
Local-first multi-agent framework with Queen-Workers-Quorum consensus architecture
Qwen-AgentWorld
World-model framework for agent environment simulation and action reasoning by Alibaba
RAGFlow
Open-source RAG engine with agent capabilities, GraphRAG, and MCP integration
Reactive Agents
Effect-TS based agent framework with fine-grained control and MCP support
Reactive Agents
Type-safe AI agent framework with Effect-TS and React Loop patterns for composable agents
Reactive Agents
Effect-TS framework for composable AI agents with React-style loops and MCP support
Reactive Agents
Effect-TS framework for composable AI agents with structured dimensions and MCP integration
ReASearch
Framework for autonomous reasoning-driven optimization across prompts, programs, and ML workflows
ReflectFact
Self-reflective multi-agent system for verifying complex factual claims across multiple sources
ResidencyRL
RL framework for training medical AI agents through simulated clinical encounters
RoboClaw
VLM-driven robotics framework for autonomous long-horizon task execution and policy learning
RTPO
Reinforcement learning framework for stabilizing multi-turn agent training through reverse credit assignment
Ruflo
Enterprise multi-agent orchestration platform with native Claude integration and swarm intelligence
ruflo
Enterprise-grade orchestration platform for Claude multi-agent swarms with RAG and distributed intelligence
Sammy SDK
Self-configuring AI agent framework that learns your codebase automatically
Sathi AI SDK
Multi-provider TypeScript framework for building AI agents with unified LLM interface
SearchOS
System-level framework preventing search loops in distributed web research agents
SkillGate
Training framework for skill selection in long-horizon autonomous agents
SKIMIX
Multi-agent framework for inference-time scaling via dynamic skill mixture and retrieval
SPADE
Self-play RL framework where LLMs design environments and solve them for continuous improvement
SpatialCLI
Framework teaching vision-language models spatial reasoning through tool use and internalization
SPD-RAG
Hierarchical multi-agent RAG system that assigns specialized sub-agents per document
SplitAgent
Privacy-first distributed AI architecture for secure enterprise-cloud collaboration
StaffForge AI Agent Framework
Write once, deploy anywhere: portable AI agents across multiple LLM providers
Synapse Agent Framework
Lightweight Node.js agent framework optimized for serverless and cloud functions
TITAN Agent
TypeScript framework for multi-agent orchestration with approval gates and Mission Control UI
TITAN Agent
Full-featured TypeScript agent framework with multi-agent orchestration and Mission Control UI
TITAN Agent
Autonomous AI agent framework with Mission Control GUI and multi-channel communication
ToolRosetta
Automated tool standardization framework bridging open-source repos with LLM agents via MCP
ToolVerse
Scalable RL framework for training agents on complex tool-integrated reasoning tasks
TopoAgent
Graph-based agent framework that evolves topological states for complex multimodal reasoning
VeriSkill
Self-evolving framework enabling LLM agents to learn and refine program verification skills
VISUALSKILL
Hierarchical skill library for GUI automation with reusable multimodal interaction patterns
VoltAgent
Lightweight JavaScript framework for building composable autonomous agents with minimal dependencies
Wunderland
Security-hardened AI agent framework with HEXACO personality modeling and 37+ integrations
Xiaoma CLI
Universal AI agent framework built for agile development workflows and team collaboration
XiaoMa CLI
CLI-based AI agent orchestrator for agile development workflows and multi-agent coordination
XSkill
Continual learning framework enabling multimodal agents to improve from experience without retraining
dev tools
(61)Agent Audit
Security analysis system for LLM agent applications and MCP configurations
Agent Memory Distillation
Training-free knowledge transfer from large to small agents via hierarchical memory
AgentBeats
Agent-based evaluation framework where AI judges assess other agents through standardized protocols
AgentDev
Lightweight AI agent framework with built-in debugger for development workflows
AgentDS
Benchmark framework measuring AI agent performance vs human experts on data science tasks
AgentLens
Interpretable safety framework for steering coding agent behavior via LLM internal representations
Agora Consensus
Multi-agent framework for autonomous bug detection in distributed consensus protocols
ai-agents-for-beginners
Microsoft's free 12-lesson curriculum for learning to build AI agents from scratch
Agent Identity Protocol (AIP)
Cryptographic identity protocol for verifiable agent delegation and provenance tracking
Agent Lifecycle Toolkit (ALTK)
Standardized middleware for production-ready AI agents with built-in failure handling
BackendForge
Benchmark framework for evaluating AI agents on end-to-end backend code generation
CapCode
Cheat-proof coding evaluation framework with performance-capped randomized tests
CausalFlow
Causal debugging framework that converts failed LLM agent traces into minimal counterfactual fixes
Change2Task
Transform merged PRs into verified coding agent tasks for training data generation
Chronary Toolkit
Universal calendar API adapters for AI agents across major frameworks
claude-code-best-practice
Production-ready best practices guide for Claude Code and agentic engineering workflows
CUA-Gym
Reinforcement learning benchmark suite for training GUI automation agents with verifiable rewards
Decoupled Search Grounding (DSG)
Vendor-agnostic architecture decoupling search retrieval from LLM reasoning for portable agents
DeltaBox
Millisecond-level checkpoint/rollback system for stateful AI agent exploration
DiG-bench
70 game environments for benchmarking AI agent discovery and experimentation capabilities
EasyOPD
On-policy distillation framework for compressing LLMs with unified teacher-student training
Echo
Learning system that refines AI agents through user feedback on interaction logs
EpiBench
Verifiable benchmark for testing AI agents on epigenomics analysis workflows
FlowArk
Context-aware knowledge reuse system for optimized Android app analysis at scale
FluxBench
Benchmark framework for evaluating AI agents on complete chip design workflows
Hallucination-Aware Layered Oversight
Zero-hallucination AI framework through architectural separation of generation and validation
HARP
Research platform for systematic HCI studies of human-AI interaction with live LLM agents
Hippo Core
Drop-in persistent memory layer for AI agents with vector storage and cross-framework support
HippoCore
Drop-in persistent memory layer for AI agents with native MCP support
HyperTool
Multi-step tool execution framework that hides intermediate dataflow from reasoning traces
ICAE-Bench
Benchmark for evaluating coding agents on end-to-end project building from vague intent
IMBench
Benchmark for evaluating AI agents on intuitive robotic manipulation tasks
IssueTrojanBench
Security benchmark testing AI coding agents against malicious issue requests and backdoors
KYA
Framework-agnostic trust and governance layer for autonomous AI systems with verifiable provenance
LH-Bench
Evaluation framework for measuring long-horizon agent workflows on enterprise tasks
MalSkillBench
Security benchmark for detecting malicious AI agent skills with runtime verification
MCP-in-SoS
Security risk assessment framework for evaluating open-source MCP server implementations
MemMA
Multi-agent memory framework with self-evolution for LLM agents
NanoClaw WebChat
WebSocket-powered chat interface for deploying NanoClaw AI agents in the browser
Needle2
Edge-optimized function calling framework for on-device AI agents
OmniaBench
Comprehensive benchmark suite for evaluating general-purpose AI agents across diverse scenarios
PAVE
Memory-efficient AI agent framework optimized for terminal and iOS environments
PIPES
Secure agent perception through data provenance tracking and authority controls
ProofAgent Index
Governance readiness index for assessing AI agent production safety and compliance
QuoteBench
Benchmark isolating LLM code generation failures from command execution errors
Replica
Auto-evaluating framework for training AI agents to replicate scientific research papers
RODS
RL-powered data synthesis for training multi-turn tool-use agents at capability boundaries
Scrapling
Adaptive web scraping framework with MCP integration and stealth capabilities
SlopCodeBench
Benchmark for measuring coding agent performance degradation across iterative tasks
SpecOps
Automated testing framework for GUI-based AI agents in real-world environments
StagedWorkspace
Versioned workspace infrastructure ensuring explicit state contracts for knowledge-work agents
Supra Router
51M-parameter routing model for intelligent multi-LLM orchestration at the edge
SWE-Explore
Benchmark for evaluating coding agents' repository exploration and code understanding abilities
TDAD
Pre-change impact analysis for AI coding agents using graph-based dependency mapping
ToolBench-X
Benchmark framework testing agent robustness with unreliable tools and error conditions
ToolPro
Program-based interface for multi-step agent-service interactions with effect types
TopoChunker
Topology-aware document chunking that preserves hierarchical structure for better RAG retrieval
Vera
Automated safety testing framework for LLM agents with risk discovery and verification
VRR-Stop
Principled stopping framework for LLM agent repair loops that prevents over-correction
WorkBuddy Bench
Multi-domain benchmark for evaluating coding agents across real-world software engineering tasks
ZEBRAARENA
Diagnostic simulation environment for testing LLM reasoning and tool use capabilities
agents
(32)AnalogAgent
Training-free agentic framework for analog circuit design automation with self-evolution
AutoGPT
Open-source autonomous AI agent framework with multi-LLM support and configurable autonomy
AutoMOOSE
Autonomous multi-agent system for running MOOSE multiphysics simulations from natural language
BettaFish
Multi-agent system for public opinion analysis, sentiment tracking, and trend prediction
DomAgent
Domain-specific code generation using knowledge graphs and case-based reasoning
EpiNarrate
Multi-agent system for translating epidemiological data into clear public health narratives
FastContext
Dedicated exploration subagent that keeps code search separate from task execution
Goedel-Architect
Agentic framework for automated theorem proving in Lean 4 with blueprint-driven proof synthesis
Hermes Agent
Autonomous AI agent with adaptive learning capabilities and Claude Code integration
Hermes Agent
Production-ready AI agent with ReAct engine and multi-provider LLM support
HLSmith
Expert-guided agentic framework translating C/C++ to hardware-accelerated FPGA code
HORIZON
Self-evolving agent framework for repository-level hardware design and EDA automation
IndustrialCoder
Specialized coding agent for hardware engineering: Verilog, CUDA, and Triton code generation
Jagarin
Mobile-optimized agent architecture with intelligent hibernation for battery-efficient always-on agents
LensWalk
Agentic video understanding framework with active evidence-seeking for LLM-powered analysis
Macaron
Personal agent with tool-use and dynamic UI generation powered by mixture-of-LoRA architecture
MechGeo
Automated formal geometry proofs in Lean 4 with GeoFormalizer and GeoProver
MLEvolve
Self-evolving multi-agent system for automated ML algorithm discovery and optimization
NVIDIA Nemotron-3-Ultra
550B parameter MoE model with multi-token prediction for enterprise conversational AI
OpenTentacles
GitHub-native AI agent framework extending Copilot for complete open-source workflow automation
Ornith
Production-grade open-source agent models from 9B to 397B parameters with GGUF support
PAVE
Terminal-based AI agent framework optimized for iOS and resource-constrained environments
PAVE
Lightweight terminal-based AI agent framework optimized for mobile and edge devices
ProSPy
Multi-agent Text-to-SQL framework for complex analytical queries on enterprise databases
QBugLM
Multi-agent framework for automated quantum software debugging with silent error detection
RT-SHCUA
Real-time self-hosted agent framework bridging computer-use AI and safety-critical UAV control
RustPrint
Documentation-guided agentic framework for repository-level C-to-Rust code migration
Sapient HRM-Text
1B-parameter hierarchical reasoning foundation model for building structured AI agents
SimWorlds
Generate dynamic 4D physics worlds from text for embodied AI training and simulation
TITAN Agent
Premium autonomous AI framework with configurable autonomy, security shields, and mesh networking
Tycho
Game-playing agent that builds programmatic world models for active abstraction and skill learning
UI-TARS Desktop
ByteDance's open-source multimodal desktop automation agent with GUI control and MCP support
mcp servers
(3)Euclid-MCP
MCP server bridging LLMs with Prolog for deterministic logical reasoning
FastMCP Prefect
Pythonic MCP framework with workflow orchestration by the makers of Prefect
Scrapling
Adaptive web scraping framework with AI extraction and MCP server integration