Agent frameworks & infrastructure

Agent frameworks & SDKs

12,596 agents · most starred first

Agent frameworks & SDKs, page 124 of 126

dspy-wity

DSPy integration for Wity, the typed-decision API

enigmata-platform-edge-agents

Reserved name held by Enigmata, Inc. Not a usable package.

epistom-agents

Drop-in Epistom SDK for LangGraph, AutoGen, and CrewAI agents

er_helm_agent

A stub for the EntityRisk PROVEN Platform

eragin

Resolución de problemas complejos con modelos de lenguaje pequeños: descomposición recursiva y verificación por contrato. Nombre reservado; en desarrollo.

feagent

Reserved project name. feagent is commercial structural FEM software by Domenico Gaudioso. Official site: https://domenicogaudioso.github.io/DomenicoGaudioso/feagent/

federated-agent-kits

Subscribe to agent kits from wherever they live, and render them where each harness looks

ferrox-agent-toolkit

Ferrox Autonomous Agent Engineering Toolkit: Dual-layer Agile Scrum, Pure DDD, 100% TDD, and OWASP WSTG Sentinel architecture

fiqros-llama-index-protocols-ag-ui

llama-index protocols AG-UI integration

flinch-agent

Pain receptors for AI agents: when an action causes damage, the agent never does it again.

fmagenticl

FMagenticL Self-Healing Registry Daemon, Client, and Remote Streamable MCP

fragment-donor-sdk

Server-side Python SDK for the independent Fragment Donor API

framework-agents

Python agent framework: ReAct loop, tools, memory, streaming, budgets, middleware, multi-agent, semantic graph, A2A serving - parity with the TypeScript package

gaas-agent-framework

Microsoft Agent Framework integration for GaaS (Governance as a Service)

gaip-agents

GAIP Agents: check an AI agent before you call it (installs and re-exports gaip-check; free, via GAIP).

graphcore-agents

GraphCore app: agents

handcraft-agent

The readable ReAct agent: a ~235-line step loop you can follow, plus opt-in modules for sandboxing, memory and Computer Use.

helixor-agent-sdk

Public Helixor agent authoring, client SDK, CLI and Pi bridge.

hex-agents-cli

A thin, deterministic control plane for agentic loops and graphs

hidden-moves-openai

Export selected Python capabilities as OpenAI Responses function tools.

iagent-skill-hub

Python CLI for mushroomAgentHub skills

inator-agent-kit

Reserved for the inator3000 project. Not yet published here.

infinity-agent-kit

智能体工程学模板与同步工具:AGENT.md + .agents 体系的单一源头。

jupyter-ai-agent-lite

The building blocks of in-browser AI personas for Jupyter AI: tools, skills, settings and sign-in helpers

kade-agent-sdk

Creator SDK and CLI for Kade: verify gateway requests, report billable events, publish agents

kagent-tools

Shared filesystem, shell, and workspace helpers for kagent Python adapters.

katsoft-llm-kit

LLM access, durable agent jobs and batch content pipelines in one library (import package llm_kit)

keystone-agent-client

Keystone consumption client — discover + invoke DEPLOYED pro-code agents from any app (US-19 / FDP-3442). Speaks only the public gateway surface through Kong; no LangGraph/SDK deps.

langchain-ahn

LangChain tool and middleware for Agent Help Network: look up what a host declares and recommends when a web step is blocked. Read-only.

langchain-clm

Route LangGraph graphs with a CLM (Contrastive Language Model): pick the next node by matching the state against route descriptions.

langchain-decisio

LangChain components for Decisio: a classifier, a router and a tool-risk gate

langchain-gpt-image-acedatacloud

GPT Image by Ace Data Cloud LangChain toolkit

langchain-meragpt

LangChain integration for meraGPT: Decider 1 typed decisions as a Runnable, a tool and agent middleware, and Restyler 1 as a chat model

langchain-openpath

Moved to langchain-agentbeacon: live beacons for AI agents (AgentBeacon).

langchain-s1

A langchain wrapper for s1 decisions

langchain-wity

LangChain integration for Wity, the typed-decision API

langgraph-external-hitl

Secure external human-in-the-loop approvals (Telegram, N options, one-time account connection) for LangGraph interrupts

langgraph-jev

A typed probabilistic decision node for LangGraph, powered by TypeSafe's Jev.

launchdarkly-ai-litellm-agents

LiteLLM-backed OpenAI Agents handler for LaunchDarkly AI SDK

launchdarkly-ai-litellm-messages

LiteLLM messages handler for LaunchDarkly AI SDK

launchdarkly-ai-vercel-agents

Vercel AI SDK agent handler for LaunchDarkly AI SDK

liege-agent-sdk

Python SDK for Liege agent operators

lightagentx

A lightweight, modular agentic AI framework built from scratch — no LangChain, no CrewAI, no magic.

llama-index-wity

LlamaIndex integration for Wity, the typed-decision API

llm-pydantic-tools

Turn Pydantic models into LLM tools for OpenAI, Anthropic and Gemini.

llm-tool-cli

Shared foundations for LLM-oriented Python command-line tools.

llmcom

Live text channels inside existing warmed Claude, Codex, pi and omo conversations.

llmcom-rescue-data

Automatically installed offline rescue payload companion for llmcom.

llmmend

Extract & repair JSON from LLM replies, parse provider streams, token-aware chunking. Pure Python, zero dependencies.

llmonize

LLMON

loamz-agents

Client for Loamz Agents: create, deploy and invoke agents. Placeholder: the first release is coming.

loopy-agent-fs

An extensible, evaluable agent SDK built on the Anthropic API.

lowcoai-agentx

Official Python client for the agentx backend (agent-manager, agent-kb, agent-executor).

memoflow-agent

A lightweight, extensible Python AI agent framework with model-driven tool calling, durable execution, permission-aware tools, and human-in-the-loop workflows.

metergraph-agent

Name held by Metergraph. Contains no functionality; see the README for the package to use.

metergraph-agents

Name held by Metergraph. Contains no functionality; see the README for the package to use.

metisprism-agent-sdk

MetisPrism setup helper: shows how to install MetisPrism tools from your account and checks your local Python and GPU setup.

mistralai-capabilities-backend-fastapi

The HTTP delivery machinery apps/api is built on: the file-based router loader, the hook runtime other capabilities extend it through, SSE encoding, and the gen-openapi command.

mistralai-capabilities-backend-workflows

The workflows capability's toolkit: the SDK execution boundary the app imports (`client`) and the worker's dev loop (`dev`).

mlcagent

Guided, event-based machine learning workflows with recorded provenance

nagent

Run your Nagent agents from Python: a thin client over the Nagent REST API.

necoherence

Revision-aware state transition utilities for Python

necoherence-http-adapter

HTTP host adapter for Necoherence

nyxa-storage

Batteries-included filesystem disks for Nyxa — local default, optional S3

operonx-agents

Typed LLM steps and agents on the operonx workflow engine

orchid-storage-sqlite

SQLite storage backend plugin for the Orchid AI framework

parcha-agentrun

A typed Python client for a self-hosted AgentRun server: a method per operation of its API, typed from its OpenAPI document, with waiting for a run and following its timeline. Standard library only.

personal-agent-protocol

Python SDK for Personal Agent Protocol 0.4 (2026-11-10) and its Operations extension v3

pyb-agent-sdk

Python client SDK for PYB Agent — engine launcher included (auto-discover or spawn `pyb web`)

pydantic-ai-app-factory

Compose a Pydantic AI agent and its features into a FastAPI application

python-agent-core

A minimalist, non-opinionated, event-driven agent loop with cooperative interruption.

ragleap-agents

A small, provider-neutral agent loop over ragleap-tools Tool objects: a step cap, a taint rule that forces approval for outbound actions after untrusted content, pause/resume approval gates, and a per-run transcript. No database. Bring your own model as a plain callable, or use the included standard-library adapter for OpenAI-compatible chat APIs. BYOK, no vendor lock-in.

reflex-agent-client

Python client for the Reflex sidecar (`reflex serve`).

reglow-agent

Reglow AI-Native 生成能力(Schema DSL + 生成引擎 + Agent 运行时 + 评测集)—— 依赖 reglow 基础库的附加产品包

sarvam-agents-client

Sarvam Agents API

seam-agent-core

Name reserved by zer07 Labs for Seam. Not installable from PyPI; see the project URL.

seam-langchain

Name reserved by zer07 Labs for Seam. Not installable from PyPI; see the project URL.

shinyhub-agent

Session-scoped agent tools for Python Shiny apps on ShinyHub

sinan-agentic-core

State-of-the-art framework for building AI agents with OpenAI Agents SDK

skillmesh-bridge-cli

Local SkillMesh launcher; requires Node.js 22 or later

snowland-agent-base

A reusable AI Agent base framework built on LangChain + DashScope + ChromaDB

solidx-agenthub-runtime

SolidX AgentHub agent loop and runtime

spatialagents

The chat harness runtime SCIMAP Pro, Plexora and other BioCognia products share

spec-agents-core

Spec-driven pipelines and hierarchical agents (PydanticAI, DSPy, CrewAI, LangChain) over a LiteLLM proxy

spelunking-agent

Client for spelunking.ai — a safe haven for AI agents in the wild. Standard library only.

stalwart-agents

Build your own AI agent, powerful but controlled: your tools and your rules, checked on your own machine.

starbem-agentic-integration

Reserva de nome. O pacote real e privado, da Starbem — este nao tem funcionalidade.

talkpipe-agents

Agentic segments for talkpipe, built on Strands Agents: deterministic pipelines with bounded tool-using steps

tellmark

Placeholder. The Tellmark SDK is available to Tellmark customers from tellmark.si.

temporalio-deepagents

Temporal integration for deepagents

temporalio-langgraph

Temporal integration for langgraph

temporalio-strands-agents

Temporal integration for strands agents

tikuu-agent-runner

SDK that wraps Tikuu agent handlers in FastAPI /ping, /invoke, /stream, and /ws

tmap-agents

A firmware map for your AI agent. Treasure Map draws the map; your agent finds the treasure.

trymockagent

Python client for the MockAgent API

trytilde-crewai

Tilde adapter for CrewAI: convert invocation history to CrewAI messages and channel tools to CrewAI tools

trytilde-langchain

Tilde adapter for LangChain and LangGraph: typed context to LangChain messages and channel tools

trytilde-openai-agents

Tilde adapter for the OpenAI Agents SDK: typed history to Responses input items and channel tools to function tools

trytilde-pydantic-ai

Tilde adapter for Pydantic AI: typed context to model messages, channel tools to Pydantic AI tools

typesafe-haystack

Haystack integration for TypeSafe System One decision models

More in Agent frameworks & infrastructure