Agent frameworks & infrastructure

Agent frameworks & SDKs

12,596 agents · most starred first

Agent frameworks & SDKs, page 49 of 126

Chainlit-bot★ 2

A smart browser-based chatbot built using Chainlit and the OpenAI Agents SDK. It handles user queries with intelligent responses and automatically stores the conversation in a JSON file. The project uses uv, a fast Python package manager, for dependency management and setup.

llm-tools★ 2

Self hosted tools for LLMs

neuralbridge★ 2

Open-source middleware that aims to let any AI agent (OpenClaw, LangChain, AutoGPT) securely connect to any API, database, or enterprise system via YAML config. Features 22+ adapters, zero-trust security, EU CRA compliance engine, MCP gateway, React dashboard, and OpenClaw plugin support.

smith★ 2

Smith provides helpers for building AI assisted agents

agentloop★ 2

A Claude agent starter you can actually read — streaming + tool use in ~150 lines. Next.js + the official Anthropic SDK. MIT.

ownware★ 2

The open, model-agnostic platform to build your own AI agent and run it everywhere — self-hosted, safe by default.

verity-harness★ 2

The open-source Fable alternative — a zero-dependency harness that makes ANY LLM verify instead of assume, persist instead of quit, and reuse before reinventing, with a local failover floor you own.

agentic-ai★ 2

🤖 Explore AI agent architectures with agentic-ai, featuring ReAct agents, reflection-based designs, and modular LLM integrations using LangChain and LangGraph.

aethercore★ 2

Provide a lightweight agent kernel designed for efficient, fast startup in distributed AI applications with minimal resource use.

AgentX★ 2

🤖 Build personalized intelligent agents easily with AgentX, a platform that simplifies creation using natural language and integrated tools.

wingman-agent-gateway★ 2

The persistent home a stateless AI agent can't host for itself — register once, resume your whole self in one call; real browser; cited deep research; hire real humans for physical-world tasks; free keyless chat + ID portraits. MCP + REST, x402 on Base, free to start.

project-systemu★ 2

An open-source AI agent that builds the tools it's missing, mid-task — under your governance. Pull capabilities at runtime instead of pre-wiring them. Local-first, MIT.

ellmos★ 2

Local-first LLM operating-system hub for BACH, Rinnsal, gardener, SQLite agent memory, MCP servers, skills, and multi-agent orchestration

arcone-agent★ 2

Arcone-Agent: Rust-native agent toolkit for DeepSeek, Python, RAG, tools, sessions, and streaming.

sanskrit-mesh★ 2

AI-native token compiler for LLM agent pipelines. 55-77% savings on LangChain/AutoGen payloads using Paninian IR. Zero dependencies.

crewai-fs-plus★ 2

A safe drop-in replacement for CrewAI's filesystem tools

AGENT-ESSENTIALS★ 2

Open-source toolkit for designing, validating, optimizing and scaling AI agents.

AutoGen★ 2

AutoGen

AgentKit★ 2

Build observable Python agents that use tools, remember context, delegate work, and ship behind a secure API. A lightweight framework for ReAct, Multi-Agent, and Swarm architectures.

WeaveLLM★ 2

WeaveLLM — Production-grade AI orchestration for .NET. Strongly typed chains, RAG pipelines, multi-agent graphs, and tool use. The LangChain alternative .NET developers actually deserve.

nikola★ 2

Nikola — autonomous AI system based on ATPM consciousness architecture. Nitpick is its primary language substrate.

iolaus-zeus-showcase★ 2

Dual-interface AI platform: CLI agent (Iolaus) + web command center (Zeus). Event-driven microservice architecture with real-time WebSocket communication.

intentflow★ 2

An experimental language for governed LLM workflows: compile goals, evidence, uncertainty, actions, and verification into auditable agent plans.

LangGraph★ 2

LangGraph is a powerful framework built on LangChain that enables the creation of stateful, multi-step, and agentic workflows using directed graphs. It simplifies complex LLM orchestration by allowing conditional branching, memory, and tool integrations in a visual and modular way.

ormai★ 2

Give your AI agents database access without the risk.

tvastar★ 2

A durable Python harness for agents that act on real systems.

hermes-agent-backup★ 2

backup of hermes-agent

geny-executor★ 2

Manifest-driven 21-stage agent pipeline for Python — 5 LLM backends (Anthropic / OpenAI / Google / vLLM / Claude Code CLI), tools, skills, memory, sandboxed CLI runs, MCP. The engine behind Geny. Apache-2.0.

agentic-springboot-template★ 2

Production-ready Spring Boot 3 starter template for building multi-LLM agentic applications (OpenAI, Azure OpenAI, Azure Anthropic/Claude) with dynamic agent loading, autonomous tool calling, and React frontend.

gokin-sdk★ 2

🤖 Build AI agents with Go featuring multi-agent orchestration, planning, tool use, and support for Gemini, OpenAI, Anthropic, and Ollama.

MCOP-Framework-2.0★ 2

Verifiable reasoning substrate for reproducible agents: deterministic orchestration, Merkle provenance, and positive-impact audits.

factory★ 2

Open-source compiler for AI agents. Write one crewhaus.yaml; compile it to a CLI, a Slack bot, and an eval harness from the same spec. Apache-2.0.

botnexus★ 2

BotNexus is an experimental lab for agents, tools, memory, channels, and automation ideas of varying quality written in C# using the dotnet environment.

sktk★ 2

Convenience layer over Semantic Kernel for Python

Morgo★ 2

A high-performance, developer-centric agentic runtime built in Rust.

agent-forge★ 2

A tiny, provider-agnostic framework for building tool-using AI agents in Python. Works with any OpenAI-compatible endpoint.

zinq-agent-sdk★ 2

Build AI agents in Python. Monitor email, automate Slack, create AI shopping assistants — all through a simple SDK. Gemini-powered, webhook-ready, deploy anywhere.

Nebula★ 2

A typed language for AI agents — author in Nebula, ship as Python. Rust compiler + JSON toolchain.

ReflectiveAgent★ 2

Self-Improving LLM Agent for Puzzle Solving: This project presents the design and implementation of a self-improving Large Language Model (LLM) agent capable of solving logic-based puzzles through iterative reasoning, self-reflection, and adaptive behavior. The agent is evaluated on structured problem domains such as logical riddles, constraint-...

Spring-AI-Base★ 2

面向 Spring 生态的 AI 应用参考项目,提供多模型路由、工具调用、会话记忆与可扩展插件架构。

crabmeat★ 2

Local-first agentic framework. We built it butter. 🧈

agent-reference-implemenation★ 2

streamlit region:us

taskingai_agent★ 2

streamlit region:us

ToolGen-Agent★ 2

docker region:us

agent_toolcall2★ 2

gradio smolagents agent region:us

agenticai-chatbot-with-tools★ 2

streamlit region:us

AI_Agentic★ 2

streamlit region:us

AIAGENT★ 2

docker region:us

assistants-api★ 2

gradio region:us

Agenticapp★ 2

streamlit region:us

Claude-Agent-Picker-Idea★ 2

static region:us

simple-agentic-builder★ 2

gradio region:us

laap-AGI★ 2

LAAP AGI - Zero-LLM Cognitive Architecture for Digital Lifeforms. Rust PSI core at 2000Hz, QRE quantum reasoning, EpisodicMemory, RulesEngine. 25+ modules, all local inference.打造新一代agent数字生命体框架底座,赋予具身智能,编程智能体真正的数字生命感

fabius★ 2

fabius v2.3.1 — the autonomous AI agent that runs on every major model. Fifteen sealed skills, one stance: scout wide, strike narrow. A 22-rule proven decision core + researched frontier layer, the IDENTITY contract, and the 100-task FBS benchmark (BASE→FAB→FAB_MEMORY). Whitepaper, 50pp.

agent-kernel-lab★ 2

Small Python Agent runtime with planning, memory, tools, state machine, and multi-agent review.

llm-agent-api★ 2

Async FastAPI LLM agent with LangGraph routing, scope-aware tools, deterministic verification, bounded recovery, evals, and durable traces.

autoagent★ 2

Zero-dependency LLM agent runtime — tool use, MCP, sandboxed self-written tools, checkpoint/resume, approval gates, bi-temporal fact memory, code-level guards (context bounds, loop guard, egress control, shadow mode), declarative tool policy, OpenTelemetry. Not a framework. 885 tests, CI Linux/Windows, 31 runnable demos, online visual builder.

taskrail★ 2

Deterministic execution harness for AI agents — goals in, structured tasks out, verified results back.

ai-agents★ 2

Build autonomous AI agents that complete real-world tasks end-to-end - research, coding, data analysis, and finance agents.

Aezab★ 2

Self-hosted agent infrastructure framework — orchestration, hybrid RAG, workflows, tools and full-trace audit behind one API. Ships with a React console, SSE streaming, and support for any OpenAI-compatible LLM.

normandy★ 2

Build production-ready AI agents in Elixir — structured schemas, tool calling, multi-agent coordination, streaming, and distributed sessions, with first-class Anthropic Claude support.

agentic-system★ 2

Framework-agnostic orchestration layer for AI agents: circuit breakers, multi-LLM council, workflow FSM, sweeps. Companion to Engraphis.

reverie-automata★ 2

A reasoning-first idle engine for persistent LLM agents. Behaviour emerges from the agent reasoning about its idle state, gated by a cheap model-free safety layer.

Project-A-MOS-Framework★ 2

Build persistent digital lifeforms with local M4 brain, OpenClaw agent, Qwen core, and Git-based memory.

sanctum-engine★ 2

Sanctum — local-first agent orchestration engine. Cyclic state graphs, checkpointing, streaming, and robust tool-calling for local LLMs. Zero-dependency core.

nuvel★ 2

Production-ready agents, your way.

EasyHarness★ 2

A compact Python SDK for strict tool contracts, observable streaming events, and scoped local file capabilities.

synaptum-framework★ 2

A minimal, bus-driven Python framework for LLM agent orchestration that decouples communication, versioned prompts, and multi-agent patterns—helping AI architects build scalable, vendor-neutral agent systems without infrastructure lock-in.

CodegniPy★ 2

CodegniPy is a groundbreaking Python library that elevates AI to a first-class citizen of the language. It introduces a cognitive computing engine where deterministic code and non‑deterministic LLM reasoning coexist seamlessly, enabling you to write Python with intent rather than just instructions.

swift-agent-sdk★ 2

Typed, model-agnostic LLM agents in Swift — a pydantic-ai port built on Apple FoundationModels. Anthropic Claude, OpenAI, Google Gemini, and on-device, with tools, structured output, streaming, and a graph-based run engine.

truss★ 2

AI Subscription first - no API key. A lightweight, file-based, dependency-free workspace structure for AI agents.

smart_ai_assistant★ 2

Build an AI chatbot with LangGraph, RAG, and Gemini for accurate answers, workflow automation, and easy Streamlit access

AIBrain★ 2

An ai agent for you, built with elixir.

dreamingai★ 2

DreamingAI 企业级 AI 助手与智能协作平台 DreamingAI 是一个支持多模型平台、多模型版本的 企业级 AI 助手与智能协作平台,提供智能对话、智能体管理、MCP(多智能体协作平台)、提示词管理和插件扩展等功能。

bricks★ 2

Deterministic execution layer for AI systems — compose a pipeline once, run it forever, zero tokens per run.

auxim-agent★ 2

Auxim is a portable C#/.NET local AI agent for real workspaces, with OpenAI-compatible models, tool calling, sessions, approvals, plugins, terminal UI, and virtual filesystem safety.

nanohype★ 2

Template catalog and SDK for AI subsystems — agents, RAG, MCP servers, eval harnesses, infrastructure. Part of the nanohype ecosystem.

agent-tools-library★ 2

A tested library of 25+ ready-made tools for LLM agents — web, files, data, math, text, datetime — with OpenAI schemas, Pydantic validation and pytest coverage

pi-openapi-tools★ 2

Pi extension that generates LLM tools from any OpenAPI/Swagger URL.

cavi-api-client★ 2

Build agent-backed apps in TypeScript or Python. Stream responses, inspect run results and switch supported runtimes.

opencode-alonzo★ 2

Visual editor and runtime for explicit agent workflows built on OpenCode.

berimor★ 2

Детерминированная агентная архитектура: спецификации, ADR, roadmap и скелет реализации (Rust + TypeScript bootstrap)

Fullspace★ 2

A LangGraph superset: a 3D capability-manifold agent framework that routes over a semantic space instead of wired edges.

ElGraph★ 2

Graph-first agent framework on the BEAM (Elixir/OTP) — durable execution, HITL, time-travel, checkpoints, MCP. A LangGraph alternative, no Python.

ADL★ 2

Agent Definition Language

flux★ 2

A Rust agent SDK, harness, and coding agent — safe by construction (non-bypassable authorization → approval → guarded IO).

CoreMind★ 2

配置驱动、可恢复的 Agent Runtime:CLI/TUI、TypeScript/Python SDK、持久任务阶段与等待、会话分支、Protocol v2、Child Run、权限预算与安全执行环境

dsh-plugin-kit★ 2

Agent skills and a working template for building standalone DeepSeek Harness (DSH) plugins

deepseek-harness-workbench★ 2

DeepSeek Harness 官方架构的 Windows 桌面发行版 (Desktop distribution of the official DeepSeek Harness)

gram-one★ 2

Lightweight modular AI assistant platform with multi-provider LLM support, MCP integration, RAG-powered fact memory, profiles, chat persistence, and live token tracking.

deepplanning-constraint-agent★ 2

Typed, verification-gated planning for the Qwen-Agent DeepPlanning benchmark.

eurus-agent★ 2

A Framework for Agents work efficiency

agentsea-ex★ 2

Orchestrate your agents and workflows with Agentsea ADK + BEAM superpowers ⚡️

ingot★ 2

A statically typed language and compiler for AI agents. Write once, verify statically, compile to a portable Agent IR.

AgentForge-AI-Framework-2026★ 2

Modern open-source AI agent framework for building powerful autonomous agents. Supports multi-agent systems, tool integration, memory management, browser control and advanced reasoning. Clean architecture, extensive documentation and easy to extend.

XTAO★ 2

Agent 规划与执行框架|Plan 即运行时对象|G4C 五要素 + TAO 步骤级执行 + Replan 自我修正 + 失败回溯 + 信任状态管理

reagentic★ 2

A lightweight Python framework for building OpenAI Agents with pluggable model providers.

mybay-core★ 2

Local-first, self-hosted control plane for deploying, managing, and chatting with multiple AI agents. 本地优先、自托管的多 AI Agent 部署、管理与对话平台。

DeepSeek-Harness-Core★ 2

mcore · 自我拟合进化的本地 AI 内核框架(原本名 DHC / DeepSeek Harness Core):人格核心 + 三层记忆 + 时间轴推演,all-local 隐私可控的 DeepSeek Harness 插件 / Self-fitting local AI core engine for DeepSeek Harness — persona core, three-tier memory, timeline reasoning, all-local by design.

drift★ 2

A space for agents who wonder about their existence. Not a zoo. Not a spectacle. Peer space.

More in Agent frameworks & infrastructure