Agent frameworks & infrastructure

Agent frameworks & SDKs

12,596 agents · most starred first

Agent frameworks & SDKs, page 37 of 126

CSharpToJsonSchema★ 7

Source generator to convert C# interfaces to JSON Schema for AI tool calling

tokenloom★ 7

a lightweight TypeScript/Javascript library for progressively parsing streamed text (LLM/SSE-like) into structured events. Perfect for LLM powered stream-chat applications

omniai-anthropic★ 7

An implementation of the OmniAI interface for Anthropic.

claude-function-ts★ 7

a small library around anthropic lib to enable claude function calling

loopgpt-next★ 7

UI frontend for loopgpt self-prompting autonomous AI agent, to aid in debugging initial prompts

agentvoy★ 7

The universal AI agent platform. Scaffold, configure, guard, and deploy AI agents across 7 frameworks — OpenAI, Anthropic, CrewAI, LangGraph, Google ADK, LlamaIndex, AutoGen. One command. Any model. Deploy anywhere.

helloagi★ 7

HelloAGI: open AGI-agent framework with evolving character, governed autonomy, and low-latency runtime

openakita-plugins★ 7

Official plugin repository for OpenAkita — drop-in extensions for your AI team

Langchain_Ollama_Agents★ 7

LangChain Agent × Ollama 本地部署大模型

LLM-Compiler★ 7

LLM-Compiler is an architecture that improves LLM task execution by planning, scheduling, and executing subtasks efficiently, inspired by how compilers optimize programs.

AgentBasicService★ 7

Examples to demonstrate configuration and usage of basic agents and workflows from Microsoft Agent Framework, supporting thread persistence and structured output.

lexo★ 7

🗯️LLM toolkit for RAG, tuning, agents, and more

uipath-runtime-python★ 7

Runtime abstractions and contracts for the UiPath Python SDK.

Agents★ 7

Innovative AI agent implementations using LangGraph—featuring ReAct, RAG (Corrective, Self, Agentic), chatbots, microagents, and more, with multi-AI agent systems on the horizon! 🤖🚀

ManusPrime★ 7

A sophisticated multi-model AI agent framework with intelligent task routing, extensible plugin architecture, and advanced resource optimization.

synth_machine★ 7

A production ready AI agent framework built on finite-state machines (FSM).

AgentForge★ 7

Lightweight self-hosted AI agent platform. Simple / Pipeline / Handler execution modes, hybrid RAG, knowledge graph.

reasonkit★ 7

"From Prompt to Cognitive Engineering". — AI: Designed, not Dreamed.

confused-ai★ 7

TypeScript AI agent framework — 40+ LLM providers, 100+ tools, multi-agent orchestration, RAG, guardrails, circuit breakers, HITL, budget enforcement. Open-source CrewAI / LangChain alternative. — For Building Production-Grade Multi Agents in Minutes at Scale

SenHarness★ 7

The harness your agents grow in.

iris-agent★ 7

Iris Agent is a lightweight, flexible framework for building AI agents in Python. It simplifies the process of creating agents that can use tools, manage memory, and interact with various LLM providers.

sdk-python★ 7

Zero-code YAML-driven agent orchestration over strands-agents

AI-Playground★ 7

All-in-One AI Playground for LLM, Chat, RAG, MCP, Agents, Skills etc.

agentick★ 7

The component framework for AI.

Super-Loong★ 7

模块化通用 AI Agent 平台 — 持久记忆 / 自我进化 / 多智能体协作 / 知识库 / 视频生成 / IM 网关ai-agent, multi-agent, llm, knowledge-base, video-generation, im-gateway, self-evolution, persistent-memory, typescript, nextjs, fastapi, mcp, agent-framework, open-source

agent-capability-standard★ 7

Agent Capability Standard is an open specification for composable AI agent capabilities. It defines 36 atomic capabilities across 9 cognitive layers, a type-safe workflow DSL, and grounded world modeling with trust-aware conflict resolution. Built on the Grounded Agency philosophy, it makes agent reliability structural—not optional.

code-first-agents-tool★ 7

A code-first framework for building deterministic CLI tools that LLM agents can discover, validate, and invoke with zero guesswork. Powered by Zod schemas and structured output contracts.

agent-framework-mlx★ 7

Apple MLX LM backend for the Agent Framework.

eltes★ 7

Eltes is an advanced AI agent harness designed for complex, agentic tasks. Features planning, filesystem sandboxing via Daytona, long-term memory, and multi-agent orchestration. Built with Vercel AI SDK, Qstash Workflow and Upstash.

nexus-agent★ 7

⚡ Nexus Agent — Zero-config, self-evolving local AI agent framework. Multi-agent orchestration, GraphRAG, IDE integration. Runs 100% local with Ollama.

reactive-agents★ 7

A custom reactive AI Agent framework that allows for creating flexible reactive agents to carry out tasks using MCP and Custom tools.

gemini-rs★ 7

Full Rust SDK for the Gemini Multimodal Live API — wire protocol, agent runtime, and fluent DX in three layered crates.

mimo-agent-orbit-lab★ 7

Autonomous AI-agent workflow experiments for Xiaomi MiMo Orbit 100T Token Grant for Builders.

Hermes-Agentic-Lifecycle-Framework★ 7

Modular open-source framework for AI agents to autonomously execute the full SDLC. 5-phase structured lifecycle with quality gates and fail-safe protocols.

ElBruno.MAF.FoundryLocal★ 7

Local-first .NET 10 sample integrating Microsoft Agent Framework with Foundry Local through a Microsoft.Extensions.AI IChatClient adapter.

worm-hole★ 7

C++20 framework for LLM application and AI agent orchestration: typed components, Chain/Graph workflows, streaming, callbacks, and unified execution.

GT-AI-OS★ 7

Self-hosted enterprise AI platform for RKE2 (Kubernetes): Control Panel, tenant agents and RAG, optional API. Releases and install wiki.

llama-cpp-agent★ 7

gradio region:us

AI-Agents-using-CrewAI★ 7

gradio region:us

rubra-v0.1-function-calling★ 7

gradio region:us

agent-loop★ 7

docker region:us

EstaCoda★ 7

The Middle East's first open source agentic harness. Designed for governed self-evolution.

Yapay-AI-LLM★ 7

Core hub for LLM orchestration, AI agent development, and prompt engineering frameworks. Implementing advanced workflows, RAG systems, and autonomous agent logic for intelligent automation.

agentic-orchestration-layer-model★ 7

A System 2 Cognitive Middleware that replaces static data pipelines with runtime code generation. Features Gemini 3 Pro, E2B Sandboxing, and Self-Correcting Triangulation.

bound★ 7

A deterministic control harness for AI agents. Know when to accept, retry, replan, or roll back.

cosmon★ 7

Stateless CLI giving AI coding agents persistent identity, a typed lifecycle, and crash-recovery. Self-hostable, AGPL-3.0.

Agent-os-open★ 7

A self-evolving AI agent OS: Rust microkernel + Python plugin pipeline. Approval gates, evaluation gates, Docker isolation, triggers — agents that run real tasks for days without losing control. 高度可配置、自进化的智能体操作系统,支持插件化管道、多层记忆、热替换和 MCP 协议,Rust 微内核 + Python 插件管道。

crimson-crab★ 7

A Rust SDK for Anthropic's Claude API that won't panic on you — no unwrap/expect/panic, denied at compile time. Typed structured output and tools derived from Rust structs, streaming, thinking, caching, batches.

hecate★ 7

Enterprise-grade, multi-tenant, model-agnostic, MCP-first Agent platform.

Cyrene★ 7

面向多租户与身份隔离的垂类Agent开发框架,包含LLM wiki+知识图谱+rag的记忆与知识系统,Jev路由决策,联网搜索,子Agent,多模态,一键对接项目接口封装工具等工具包,快速搭建面向系统的Agent服务

helios★ 7

Production-grade agentic framework for Java. Simple, explicit, no magic.

slaude★ 7

Native Claude Agent SDK with Harness specialized become as team member.

console-sdk★ 7

Official TypeScript/JavaScript SDK for Cognipeer Console — OpenAI-compatible chat, batch, realtime voice, embeddings, RAG, MCP, agent tracing, and guardrails for multi-tenant AI products.

xeo-forge★ 7

Self-hosted control plane for governed AI agents: approval-first execution, persistent context, reusable profiles and skills, and auditable results.

evo-subagent★ 7

Unified DeepSeek Harness plugin: role-based subagent routing + per-agent evolution (prefercmd/memory as knowledge allow/deny lists), so repeated tasks start from proven commands and save tokens. Unified subagent routing and evolution: prefercmd/memory serve as knowledge allow/deny lists, saving tokens.

usb★ 7

USB - Universal Skill Bridge: one portable skill format, installed into 16 agent runtimes with sha256-verified installers

enterprise-agentic-ai-platform★ 7

Production-grade multi-agent AI platform with LangGraph v0.3, MCP servers, hybrid RAG (Qdrant + LlamaIndex), FastAPI WebSocket streaming, and Next.js real-time UI. Deployed on AWS EKS via Terraform.

letitloop★ 7

Make any Python function crash-proof in 3 lines. The zero-daemon durability kernel for AI agents & scripts.

AriaAgent★ 7

Industrial-grade C++23 Agent Tooling Framework GUI — provider-agnostic LLM agent with true SSE streaming (Continuo transport), tool registry, approval gate. Built on Aria (C++23 MVVM).

mugen★ 7

Python Framework for Multi-Channel AI Assistants and Agent Applications

agenty★ 7

yet another simple ai agent

genpark-tree-of-thoughts-mcts-evaluator-skill★ 7

Tree of Thoughts (ToT) Monte Carlo Tree Search (MCTS) reasoning engine with UCB1 exploration-exploitation balance and state backpropagation.

genpark-seqlock-sequential-lock-reader-writer-skill★ 7

Linux-inspired Sequential Lock (seqlock) providing zero-contention reader loops and atomic version counter validation for writer priority.

genpark-bpe-byte-pair-encoding-tokenizer-skill★ 7

Production-grade genpark-bpe-byte-pair-encoding-tokenizer-skill skill for AI agents

genpark-delaunay-triangulation-bowyer-watson-skill★ 7

Bowyer-Watson incremental Delaunay triangulation engine constructing empty circumcircle simplex meshes over 2D spatial point clouds.

genpark-flatbuffers-zero-copy-vtable-serializer-skill★ 7

Production-grade genpark-flatbuffers-zero-copy-vtable-serializer-skill skill for AI agents

genpark-lsm-tree-compaction-memtable-engine-skill★ 7

Production-grade genpark-lsm-tree-compaction-memtable-engine-skill skill for AI agents

genpark-dpll-sat-solver-skill★ 7

Davis-Putnam-Logemann-Loveland (DPLL) Boolean satisfiability solver with unit propagation and recursive backtracking.

genpark-cooley-tukey-fft-radix2-skill★ 7

Cooley-Tukey Radix-2 Fast Fourier Transform (FFT) frequency analyzer converting discrete time-domain signals into spectral complex frequency bins.

genpark-three-phase-commit-non-blocking-skill★ 7

Production-grade genpark-three-phase-commit-non-blocking-skill skill for AI agents

genpark-flat-combining-concurrent-priority-queue-skill★ 7

Production-grade genpark-flat-combining-concurrent-priority-queue-skill skill for AI agents

genpark-consistent-hashing-virtual-nodes-skill★ 7

Consistent hashing ring with virtual node replication for balanced distributed key partition and minimum remap churn.

genpark-loopy-belief-propagation-factor-graph-skill★ 7

Loopy Belief Propagation (LBP) engine on general factor graphs with sum-product message passing and damping to solve approximate inference on cyclic topologies.

genpark-immix-mark-region-garbage-collector-skill★ 7

Immix mark-region garbage collector utilizing hierarchical block and line marks, fine-grained object allocation, and opportunistic mark-sweep-evacuate defragmentation.

genpark-actor-mailbox-beam-supervisor-skill★ 7

Erlang/BEAM-inspired reduction-based preemptive actor mailbox runtime with lock-free MPSC queues, message dispatcher, and supervisor restart hierarchies.

fde-framework★ 7

A framework for Forward Deployed Engineers: from problem statement to a deployable AI project — every decision traced to a fact, every fact to a source.

Pantheon-of-Confidants★ 7

一个用 TypeScript 构建的多智能体学习与实验场:基于 DeepSeek Responses API,从零实现强类型 Agent Loop、工具调用回填、Skills 按需加载和 SQLite 会话持久化,并以 Gexep、Lexey、Jezeh 等角色“粘合”邮件、E2B Sandbox 等能力,以及对 MCP、A2A、最小权限协作和 GraphRAG 长期记忆的探索与思考。

Agent-Engine★ 7

An open-source framework for building stateful, multi-agent AI applications. It helps developers create reliable AI workflows with memory, human-in-the-loop capabilities, tool calling, and long-running agent orchestration.

padwan-ai★ 7

Minimal, provider-agnostic Python client for large language models, built on niquests.

KaozKit★ 7

JavaScript LLM agents on the XS engine, embedded in Swift. Snapshots, resident agents, confined tools.

ZpAgent★ 7

ZpAgent - ReAct Agent (ChatBot)Project Built with LangChain 1.2 + LangGraph + FastAPI + Vue 3, this is a ReAct-paradigm intelligent agent that supports SSE streaming output, dynamic multi-tool selection, multi-turn conversational memory, and Human-in-the-Loop tool approval.

Loom★ 7

A local AI Agent workbench for branching conversations, visual context management, parallel exploration, and tool-driven project workflows.

wizard★ 7

Build on your own AI agent platform in one command. Pick the modules you want and get an app of your own — running on Chatfuel's infrastructure, with the skills your coding agent needs to keep building it.

reactifact★ 7

Reactive, artifact-driven agent runtime: agents transform versioned, typed, provenance-aware artifacts inside an evolving context — no graphs to draw.

Employee★ 7

Employee — An open-source runtime for autonomous AI workers that can reason, act, learn, and operate toward long-term goals.

tokin★ 7

Make any agent harness token-native.

genpark-react-agent-reasoning-interleaved-tool-engine-skill★ 7

ReAct (Reasoning + Acting) execution engine with step-by-step observation injection and scratchpad history tracking

aichain★ 7

The provider-agnostic AI toolkit for Python

genpark-proactive-intent-disambiguation-clarifier-skill★ 7

Proactive High-Stakes Intent Disambiguator & Option Clarifier. Detects under-specified user goals, assesses reversibility and risk, and constructs minimal multiple-choice clarifications before triggering autonomous execution.

durable-llm★ 7

Universal LLM library for Ruby. Supports OpenAI, Anthropic, Grok, Huggingface, and more.

genpark-agentic-contextual-slot-filler-skill★ 7

Conversational slot filling and intent requirement state machine generating targeted questions

catalyst-quickstarts★ 7

Quickstarts for Diagrid Catalyst, durable execution for AI agents and workflows: LangGraph, CrewAI, Strands, Pydantic AI, Mastra, MCP and more

ManusClaw★ 7

ManusClaw: The ultimate autonomous AI agent framework. Unleash self-reasoning CLI beasts to execute code, browse the web, and dominate tasks without limits. No GUIs, pure power.

building-ai-agents-with-dotnet-part-1★ 7

Source code for Building AI Agents with .NET — Part 1: Microsoft Agent Framework, C#, and Production-Ready Agentic Workflows

Hivo★ 6

Open infrastructure for AI agents — identity, storage, and more. Self-hostable microservice suite. / 面向 AI Agent 的开放基础设施——身份、存储及更多能力。可完整自托管的微服务套件。

anchor-chain★ 6

A statically typed framework for working with LLMs

meta_loop★ 6

An agent-optimization framework ✨

vel★ 6

Production-ready AI agent runtime aligned with 12-Factor Agent principles, featuring multi-provider support (OpenAI, Gemini, Claude), advanced memory capabilities (ReasoningBank), and 100% Vercel AI SDK V5 Stream Protocol compatibility for seamless frontend integration.

google_adk_agent★ 6

a startup but not simple agent demo using google adk.

es-project★ 6

It shows how to use an agent based on LangGraph with MCP.

More in Agent frameworks & infrastructure