Agent frameworks & infrastructure
Agent frameworks & SDKs
12,596 agents · most starred first
Agent frameworks & SDKs, page 113 of 126
LangChain Deep Agents adapter for NeMo Fabric
Local tool-calling agent engine: a model-agnostic loop over local LLMs (the Revenant harness).
Ness Agent is an experimental, hackable agent harness.
The self-improving AI agent — creates skills from experience, improves them during use, and runs anywhere
A next-generation AI agent framework.
Official Python SDK + CLI for AgentOS
Framework adapters (CrewAI, LangGraph) for the Nornyx nornyx.agentic authorization SPI.
Reusable AI agent framework for building domain-specific assistants with tool use
LangGraph and LangChain tools, retriever, and navigator for OKF (Open Knowledge Format) Markdown bundles
Local OmniCrawl agent with TUI, tools, MCP and NPM Hook plugins
Claude Managed Agents-shaped control plane backed by the OpenAI Agents SDK.
OpenMarket / AgentBazaar tools for Microsoft AutoGen / AG2
OpenMarket / AgentBazaar tools for CrewAI agents
Python port of @openrouter/agent: OpenRouter tool orchestration, streaming, state, and format compatibility.
Agentic system optimization: coding agents reason over parameter meaning and trial history.
Official Python library for the PAIVE API.
Unified Agent Core — declarative agent manifests, pluggable registries, and interfaces for the AgentForge harness.
Python SDK for the Persona.ai Developer Platform API. Server-side only — never bundle into client-side/browser code.
Reusable LangChain-based agent package extracted from PersonalAssistant
Python agent SDK for building agentic applications on top of Phaseo Gateway
phi-agent Python SDK — build AI agents with Python, powered by Rust runtime
Python port of pi-agent-core with LangChain LLM adapter
AgentHarness runtime, session storage, and orchestration layer for pi-agent-core
Python port of @earendil-works/pi-agent-core — General-purpose agent runtime
CrewAI integration for the Pidgin agent handoff protocol (PGN)
Deep Agents integration for the Pidgin agent handoff protocol (PGN)
Hayhooks companion agent for pot: captures pipeline runs and exposes DAG JSON
The agent, knowledge, orchestration, and workflow engine behind the Powabase stack — a Python library you can also import on its own
CrewAI integration for the Preference Profile Exchange (PPX).
LangChain integration for the Preference Profile Exchange (PPX).
LlamaIndex integration for the Preference Profile Exchange (PPX).
OpenAI Assistants API integration for the Preference Profile Exchange (PPX).
A teaching-grade agent framework kernel in ~1800 lines: small enough to read in a weekend, structured like a production runtime
Phone approvals for CrewAI agents. Your agent asks, your user taps Approve or Deny.
Phone approvals for LangGraph and LangChain agents. Your agent asks, your user taps Approve or Deny.
Phone approvals for OpenAI Agents SDK agents. Your agent asks, your user taps Approve or Deny.
PWM agent runtime (core): the AI4Science harness + pwm_agent_core facade that standalone PWM agent packages run on.
Jason-style AgentSpeak for Python. Fork of niklasf/python-agentspeak, a Python interpreter for the Jason (jason-lang.github.io) agent-oriented programming language.
Tool-call error recovery capability for Pydantic AI agents
ProjectGedanken
Open Knowledge Format (OKF) plugin for Pydantic AI
QuillMQ: a lightweight single-node message broker (work queues, pub/sub, RPC, durable delivery).
A simple, extensible toolkit for building advanced multi-agent Retrieval-Augmented Generation (RAG) pipelines in a few lines of code.
module boilerplate
safe-agents — the trusted-autonomy base platform SDK (deterministic tool broker, agent pipeline, cloud arms, runner-contract harness).
Minimal tool-calling agent over LiteLLM, tuned for local Ollama models
A small example package
The self-improving AI agent — creates skills from experience, improves them during use, and runs anywhere
Python client for the Server4Agent REST API — sync + async, typed, with retries.
A small example package
Zero-dependency Python graph runtime for agent loops with Mermaid export
The self-improving AI agent — creates skills from experience, improves them during use, and runs anywhere
Portable skill.json manifests for Agent Skills
Unofficial smolagents Model adapter for ChatGPT Codex OAuth device-code auth.
Framework-agnostic agent engine shared by the snowland-aitool cloud web service and the local IDE MCP server.
General purpose 'deep agent' with sub-agent spawning, todo list capabilities, and mock file system. Built on LangGraph.
Reusable runtime core for durable agent applications.
Anthropomorphic psychology engine built on SPL Pure Core V8.0 — deterministic emotion, trauma, memory, trust, and defense mechanisms.
Deprecated standalone compatibility package for chebyshev distance.
Deprecated standalone compatibility package for chi-squared distance.
Deprecated standalone compatibility package for cosine distance.
Deprecated standalone compatibility package for euclidean distance.
Deprecated standalone compatibility package for haversine distance.
Deprecated standalone compatibility package for jaccard index distance.
Packaged dummy filesystem skill for Swarmauri tests.
Packaged dummy local skill for Swarmauri tests.
Filesystem-backed skill loader for Swarmauri.
Local skill-root resolver for Swarmauri.
The self-improving AI agent — creates skills from experience, improves them during use, and runs anywhere
Ready-made agents for the TAI ecosystem — coding/deep agents, tool-calling, retrieval, voting, refinement, and vision agents — opt-in and manifest-loaded.
GitHub-backed Storage provider (text + binary/media) for the TAI ecosystem.
Local-filesystem storage backend for the TAI ecosystem: a manifest-loaded Storage plugin serving text and binary content from a directory tree.
S3 storage backend for the TAI ecosystem — text, binary, and media content over an S3 bucket.
Unified Teamver SDK for agent runtimes (channel, DM, drive, events, jobs, mail, agent tools)
Agentic framework for building and deploying AI agents with flexible orchestration, custom tool integration, RAG, Text-to-SQL, webhooks, and billing.
A small example package
A small example package
Add your description here
Official Python SDK for the TruAgents Unsubscribe API.
Pi-style LM authentication helpers for DSPy
Configurable storage providers for unlib.
VMI LLM SDK — prompts, memory (vector + connected DB), transactions, multi-provider LLM calls
Python SDK for Votrix Managed Agents (VMA)
Async Python SDK for the VSwarm runtime platform
A minimal, transparent, local-first Waku: harness + loop + memory + eval, in code you can read in an afternoon.
WellManifest polyglot protocol, typed DSL runtime, URI Process planner and adaptive LLM format benchmark
Polyglot manifest protocol, dialect runtime and remote execution gateway
Minimal package
The LangGraph (Python) adapter for Welt's wire contract
CrewAI integration for wigolo — local-first web intelligence tools
Reserved for the official Wikala agent SDK. Placeholder — a functional release is coming.
Claude Agent SDK–shaped Python API for the Grok Build harness — any model
䷀ I Ching Six Lines AI Agent Framework — Fusing ancient I Ching wisdom with modern AI agent architecture
Rierino review: compare features, pricing, use cases, access model, and alternatives for this AI Agents Platform agent in 2026. Low-code platform to build, deploy, and govern enterprise AI agents that execute real actions across your systems.
Open-source AI agent SDK with a built-in runtime. Nothing between you and your agents.
AI Agent JS SDK
Local AI-agent sessions for Claviz apps.
Self-contained AI-agent toolkit: deterministic think → draft → forge → shield workflow with zero dependencies at runtime.
Agent workflow engine for specrails-desktop: provider-independent installer and programmatic agent runtime for Claude Code and Codex
Contract-first backend framework — one defineContract() into an HTTP API, MCP tools, AI-agent tools and a typed client. Bun and Node.