Agent frameworks & infrastructure
Agent frameworks & SDKs
12,596 agents · most starred first
Agent frameworks & SDKs, page 45 of 126
The open package registry for AI agent capabilities. Discover, resolve, and install trust-verified upgrades.
An open, portable specification for describing AI agent workflows using a human-readable text language.
Portable domain contracts for steerable, evidence-backed agent execution
A lightweight, protocol-based AI agent framework with LangChain/LangGraph integration, powered by Pico-IoC dependency injection.
Go SDK contracts for typed, observable, and resumable agent workflows
Embodied AI agents runtime
The Ollama Plugin Extension for Hexabot Chatbot / Agent Builder that provides a custom block for Generative AI + RAG
An open-source package that allows developers to easily integrate the power of OpenAI's state-of-the-art AI models into their Dart/Flutter applications.
OpsAgent
Unofficial LangChain for Rust — the easiest way to write LLM-based programs in Rust, powered by Tokio, standard async, agents, RAG, tools, and integrations.
Requirements discovery as an Agent role: Scout-driven dialogue turns vague ideas into implementable, verifiable requirements - Anchorlaw's upstream input contract.
RegEx-based fuzzy command / response handling for conversational chatbots
Python package for creating chatbots. (Including discord bots)
a python module to develope your chatbot easily with image maker and code editor
(Legacy) A Python framework for a GPT implementation (although any LLM could be implemented) that determines which commands (functions) it must run to fulfill the user's instruction, using a graph. Create new commands easily by describing them using natural language and coding the functions corresponding to the commands.
Go-based LLM agent runtime with web chat, HTTP API, Discord and Telegram bots, MCP tools, multimodal support, provider failover, and persistent memory.
Local-first, Codex-native agent foundry and knowledge OS for creating reviewed, testable specialist AI agents.
Prudence, a custom harness powered by Microsoft Agent Framework. Includes a "counsel and craft" mode which delegates executive function to Microsoft Foundry and task completion to local models.
DialogBERT implemented by TensorFlow
rasa custom components to support multiple languages and multiple text scripts
LLM leveraging OpenAI API to be used in Glific via webhooks
Terraform-style plan/apply for agent systems: versioned YAML for agents, tools, workflows, and policies; local-first SQLite state; MCP & HTTP tools; structured traces.
Go 1.25製のCGOなし単一バイナリAIエージェント
Equaxis: a governed, observable and reliable agent runtime powered by Pi.
Prudence, a custom harness powered by Microsoft Agent Framework. Includes a "counsel and craft" mode which delegates executive function to Microsoft Foundry and task completion to local models.
A modular AI reasoning framework for structured thinking, expert orchestration, verification, and high-quality problem solving.
Typed Determinism for Probabilistic AI
A from-scratch Python agent harness: tool orchestration, multi-agent routing, session lifecycle, event-driven hooks, and cross-session memory recall.
AgentDeck SDK: the execution layer for agentic software. Agents, tools and workflows as plain Python, with sessions, streaming, events, human approval and run control.
基于 DeepSeek /responses API 的 TypeScript AI Agent 最小运行时:多轮对话 + 工具调用(web 搜索 / shell / 询问开发者),shell 命令在 Docker Sandbox 中隔离执行,API 文档直译的类型契约保证编译期强类型。
An enterprise workbench for the DeepSeek Harness: AI employees, knowledge bases, skills, MCP servers and DSH plugins, all manageable from a running session.
Open-source, multi-tenant AI agent platform on AWS Bedrock — visual agent builder, RAG knowledge bases, evaluation suite, and omnichannel delivery (SDK widget, REST API, WhatsApp, Telegram). Self-hosted, MIT licensed.
Enterprise-grade conversational AI platform built with Django REST Framework, Next.js 15, LangChain, and PostgreSQL with pgvector, featuring Docker orchestration, Celery task queues, and production-ready architecture patterns for scalable AI chatbot deployments.
TAC is not a language for writing code. It is a language for thinking like an agent. (The TacFlow Agentic Code) is a domain-specific language (DSL) designed for autonomous AI agents within the TacFlow swarm ecosystem. It is not intended for general-purpose programming.
A modular AI agent framework built on Vercel AI SDK. Zero-config agents with real tools, durable workflows, and HTTP interfaces.
Bedside: manners for AI agents that operate tools for smart, high-judgment non-experts. Ship and test, not only write.
12 production-grade AI agent patterns in pure Python — ReAct, planner-executor, reflection, routing, memory, guardrails — on free NVIDIA NIM APIs
Disciplined task pipeline for AI agents: SPEC interrogation, self-contained tickets, proof-based execution, replan, retro. EN/RU docs.
An experimental configuration layer for intent-driven development.
[中文化]
Build durable agent harnesses so smaller models can do repeatable, verifiable work — a versioned folder with tools, guardrails, validators, and measured evidence from every run.
ai-agent java
Implementation of Chatbot using Intent Classification.
A zbus-style message bus that keeps external integrations out of the OpenHuman kernel's dependency graph.
Self-hosted AI agent platform with a web UI. Agents, tools, MCP, Jobs, and Sites — one container, SQLite or PostgreSQL.
Multi-server MCP-based AI agent with LangGraph, supporting tool-augmented reasoning, RAG (ChromaDB + Ollama embeddings), web search (Tavily), market data (Yahoo Finance), weather APIs, and a modular multi-server architecture.
Minimal agent that runs in pi on exe.dev VMs
极简 AI Agent 框架,支持多租户,适用于企业数字员工。
Consciousness Loop — the self-firing executive of an agent: wake → integrate the organs → decide → act → set its own frequency → sleep. The keystone of agent-nervous-system. Functional, not phenomenal.
Python runtime for multi-agent LLM systems — commands, workers, MCP, memory, Apache SDK.
一个可直接使用的 Agent Skill。涵盖六大生物启发模式、六大设计原则,以及可落地的操作手册。
docker region:us
A self-improving harness for any LLM, in one Rust binary. Persistent Lua REPL as the single tool, three-level memory, persistent sub-agents, enforced budgets, external verification, per-process sandbox, and post-run reflection over its own store. Built from the YC Harness Club talks.
Easy AI integration for devs.
通过Eino+gin实现的AI agent
非官方的AgentScope Rust重构
An agent with an executive function. Metis uses a core reasoning matrix to decide how to think, dynamically creating its own perceptual faculties for each problem. This is a new architecture for building autonomous agents whose strategy and identity emerge directly from a symbolic protocol.
Lightweight LLM harness/agent paradigm built with Golang.
A framework to build event-driven AI apps
DSH plugin: register TypeSafe Jev (System One decision model) as an agent tool — jev_decide returns calibrated probabilities (noul/choice/score) for routing/triage/guardrail judgments, no text generation. 把 TypeSafe Jev 决策模型注册为 DSH agent 工具
Rust-core agentic framework with durable journal, exactly-once replay, Ed25519 A2A identity, and MCP tool server. Bindings for Go, Python, TypeScript, .NET, and Java via C ABI.
A programming language designed for AI agents
A typed language for LLM agent systems on BEAM: effect-row tracking, auditable tool effects, typed actors, and OTP supervision, queryable by agents over MCP.
企业级 AI Agent 全生命周期管理平台
A Cloudflare-powered AI agent. Inspired by Hermes.
An LLM interaction library that makes you feel like a star
Put a personal agent inside your product, at 1/1000 the cost. Personal agent infra that runs VM-less personal agents on Cloudflare: Agent Mail, WeChat, Telegram, cloud browser, long-term memory.
A tool-calling agent harness that keeps working when tools fail. Retries, timeouts, loop detection, and honest error reporting, benchmarked against injected failures.
An integration platform for agent harness orchestration: run Codex, Claude Code, and ACP agents from one desktop workspace, with shared sessions, memory, and subtask routing across them.
Typed TypeScript/React client SDK for Agentflow. Covers invoke, streaming, threads, memory, files, and graph ops, with React hooks for token-by-token streaming and client-side tool execution.
Find which tools your LLM agent confuses and fix their descriptions with proof
Canonical Python layer for AI agent tools - function to JSON Schema, once, everywhere. OpenAI, Anthropic, MCP, LangChain, FastMCP.
跑在自己电脑上的常驻 AI 伙伴:跨会话记忆(L0-L3 + 向量召回)、QQ/飞书/企微里像活人一样在场、定时任务、用自己的音色回语音、云端/本地模型混用。A resident AI companion that chats, remembers and gets things done.
Production-ready template for a self-hosted Agent Protocol server: FastAPI + LangGraph + PostgreSQL (+ optional Redis), clean-architecture layering, dual graph-authoring paradigms, staged writes, generative UI, and a CopilotKit demo frontend. E2E-tested with real SDK clients.
A small, plantable (parasitic but only in a good sense kefir) culture for development through self-observation.
Nesti runs as an advisor through MCP tools or as an autonomous orchestrator for issues. It grounds its work in a hierarchical RAG built on vector databases.
Meta-Problem Modeling (MPM) cognitive flywheel as a resident engine for LLM agent runtimes. 六阶段问题生命周期 · ε-δ 双判据收敛 · 代谢账本 · 导师规则层
TypeScript SDK for AGNT5: build reliable AI agents and durable workflows with checkpoints, retries, streaming, tools, human-in-the-loop, and evals.
Origin Workbench - local AI agent workbench forked from Multica
Python SDK for AGNT5: build reliable AI agents and durable workflows with checkpoints, retries, streaming, tools, human-in-the-loop, and evals.
MCP-native multi-agent AI platform: tool registry, human-in-the-loop approvals, execution traces, eval harness, live dashboard. Local + cloud models.
Go SDK for AGNT5: typed workers, durable workflows, agents, tools, MCP, streaming, and evals for reliable AI systems.
Shared Rust core for the AGNT5 SDKs: worker lifecycle, durable workflow checkpoints, LLM providers, eval scorers, telemetry, and MCP.
autonomous cognitive agent. perception, reasoning, action.
Rust AI agent framework and self-hosted web console with MCP, Skills, sandboxed execution, persistent sessions, tracing, and file delivery.
Local-first AI harness and agent orchestrator — workflows, plugins, and agent dispatch over ACP.
Enterprise-grade Autonomous Agentic AI Platform with LangGraph multi-agent orchestration, Agentic RAG (reranking + semantic cache), CNN vision, secure sandboxed code execution, and full observability.
Multi-modal AI ecosystem architecture — CNN perception, agentic RAG, LLM orchestration, CI/CD pipeline, zero-trust security, and live status API. Built by NIKHIL CHARY SRIRAMOJU.
Agentic AI routing lab — Dijkstra/BFS/A* with RAG + CNN topology intelligence, containerized with Docker
Your agent has agents. A self-hosted, local-first AI agent platform in one Go binary: agents hand work to specialists and build the tools, agents and apps they lack, with sandboxed tools and credentials the model never sees.
OAuth integrations & connectors for agents
Open-source Java AI Agent framework & workbench. Build production agents from the model layer up: ReAct + Harness runtime with HITL approvals, sandbox and resumable streaming, MCP/HTTP tools, ChatMemory, tracing and session replay.
Open-source, self-hosted AI agent workbench. One tool layer powers your team's chat, your app's agent, and any MCP client — add a capability by writing one file.
agent harness — multi-provider, streaming, 47 tools, autonomous tasks
Install AI capabilities, not libraries. Versioned, reusable AI components with a dependency-free CLI.
Governed AI orchestration for Node.js — build, run and govern production AI agents with built-in access control, audit trail and human-in-the-loop.
Agent-first TypeScript library for safe SaaS API connectors: typed actions, pagination, retries, rate limits, and LLM tools. MIT.
Plataforma para operar agentes de IA em produção: agentes, times multi-agente e workflows versionados com rollback, RAG com pgvector, ferramentas via MCP, guardrails e analytics de latência e custo.
Explore the integration of semantic routing with graph-based configurations using Semantic Router and LangGraph. This project demonstrates advanced routing techniques for applications in chatbots, text classification, and NLP, providing a robust framework for developers.