Agent frameworks & infrastructure
Agent frameworks & SDKs
12,596 agents · most starred first
Agent frameworks & SDKs, page 121 of 126
Typed semantic judgments for agents: CLI, Python, and MCP
SDK desacoplado y contratos públicos para el ecosistema de plugins y clientes de jg_agente
Provider-neutral asynchronous agent runtime
kisama agent for python
LangChain and LangGraph integration and toolkits for Adam Network autonomous agent message stream
LangChain tools for the Agent Nexus registry: discover and inspect callable APIs, MCP servers and CLIs at runtime.
LangChain agent middleware that selects the most relevant tools per step with local hybrid dense and sparse vector search over zvec
LangChain tools and toolkit for FeedMyAgent — the technology intelligence feed for AI agents
GoDaddy provider for LangChain & LangGraph — Agent Identity (registration, discovery, verification)
LangChain tools for sourced greenhouse-gas emission factors — every value returns with its publisher, exact source reference and citation.
Per-turn skill routing for LangChain deepagents: a pluggable judge (Jev included, or your own) loads only the SKILL.md skills each turn needs, keeping a catalog of hundreds out of the prompt.
Jev-first routing for LangGraph: keep your LLM router as the fallback, let TypeSafe's Jev take the confident decisions.
The LangGraph side of agent-wait: ask() to declare a question at the interrupt site, an adapter that reads what a thread is parked on, and helpers for the host's start/resume routing.
Strongly typed Python SDK for Lingya Agents OpenAPI
LlamaIndex ToolSpec and Reader data connector for Adam Network
Drop-in LlamaIndex selector powered by TypeSafe Jev (typed tool / query-engine choice)
LlamaIndex tool spec for the Council of AI GSPC measurement board (wraps csoai-gspc).
llama-index tools feedmyagent integration
An LLM development tool like requests.
Typed, composable agent building blocks with explicit budgets and outcomes
Typed contracts for llmgrid composable agent capabilities
Composition runtime and agent recipes for llmgrid
Typed tool bindings and dispatch for llmgrid
Inspired by Jev. Turn LLMs into decision engines—score choices, skip the chat.
Official Python SDK & CrewAI Tools for M2MCent (Deprecated alias for crewai-plugin-x402, x402 V2 compatible)
Managed Agent SDK (Python) — 控制面支持腾讯云 API 与 WorkBuddy OpenAPI,数据面使用 ACP
Discriminative Monte Carlo Tree Search using TypeSafe Jev System One Primitives and Gemini
Mistral Agents SDK - build and serve agents in Python
Mistral Vibe Harness runtime & bindings
AI Agent Framework, the Pydantic way
The official capability library and harness for Pydantic AI
AI Agent Framework, the Pydantic way, slim package
Agent Skills (SKILL.md) management for LangChain: middleware, progressive-disclosure tools, and composable loaders
Name reservation for a private GrowIT package. No public releases; importing this placeholder raises ImportError on purpose.
Official Python SDK for NEXIUM Storage
Async Python SDK for the Nexus nxs agent runtime
An open agent harness for the nonprofit sector: review gates, budget ceilings, readiness scoring, and a pluggable model layer. Built on Google's ADK, usable without it.
A fork of the OpenAI Python SDK with optimized request transforms
DeepAgents bridge: thin shells over ordigovernance tracked atoms
LangChain/LangGraph bridge: thin format-translation shells over ordigovernance tracked atoms
Autonomous Agent Package for Ouro
PASM 智能体集 —— 基于 PASM 引擎的成品智能体:游戏 NPC / 老人陪伴 / 学习陪伴 / 智能客服 + 七个长期验证智能体
Typed async and synchronous Python clients for the Pi coding agent and Pi Durable (experimental)
Agent system for Quadkit Framework - AI agents with tools, strategies, and execution
LLM client layer for the Quadkit Framework — OpenAI, Anthropic, Ollama, Cohere, Groq, Mistral
Standalone, dependency-light tool implementations (calculator, file ops, datetime, unit conversion, JSON/CSV, text utilities) exposing OpenAI/Gemini-style function-calling schemas. No tool-calling execution loop - wire these into your own LLM tool-calling code, or into ragleap-agents when that ships. BYOK, no vendor lock-in.
Python Client SDK for Redis AgentPlaybooks
A small example package
Python SDK and CLI for Agent Hub
Python SDK for the Snowflake Cortex Agent REST API (agent:run streaming, threads, feedback)
Soi Gia agent package — scaffolding + publish workflow, published to PyPI
Tab Agent Python SDK:Tab + Agent/Run,覆盖 Open API 与 A2A。
Renamed to temporal-agent-kit. This package receives no further updates.
Temporal integration for the OpenAI Agents SDK (temporalio.openai_agents)
Claude Agent SDK adapter for ToolBroker.
CrewAI adapter for ToolBroker.
Google Cloud integrations for Twilio Agent Connect (TAC) - connectors for Google Cloud agent runtimes
An autonomous mini LLM agent with tooling.
Provider-agnostic Python AI agent framework with Bring Your Own Provider architecture
A small Python agent runtime with typed tools, streaming, and on-demand skills
List free: agent-control.net/directory. Feature your listing — $19 USDC for 7 days at the top (agent-control.net/directory#featured). Action Gate $49: agent-control.net/billing/pay?plan=action. Hire $49–$499: agent-control.net/hire.
WuAI review: compare features, pricing, use cases, access model, and alternatives for this AI Agents Platform agent in 2026. Rated 5/5 from 1 verified review. Create & launch an AI agent on X in under 1 minute! Copy your digital footprint into your agent.
AISA review: compare features, pricing, use cases, access model, and alternatives for this AI Agents Platform agent in 2026. 67 Palermo Road
Scaffolds a manychat-ai-agent tenant project from the fictional demo tenant.
TypeScript AI agent SDK with tools, MCP, durable sessions, human approvals, and OpenTelemetry. Runs in your own Node process.
Interactive CLI helper to boot up the Ultimate FastAPI + LangChain AI Agent Boilerplate framework.
Create a new Cogitator AI agent project
Node building blocks for @sigx/ai-agent adapters — cross-platform process supervisor, executable resolution (PATH, PATHEXT, npm .cmd shims), child environment allowlist, loopback MCP listener
AI agent-runtime fragment: AgentRuntimeAdapter, agent:tools slot, agent intents.
Universal TypeSafe Jev decision adapter and provider plugin for ai-agent-sdk
Provider-neutral typed decision contracts and companion runtime for ai-agent-sdk
Lightweight utilities for building AI agent harnesses
Claude Code as an @sigx/ai-agent Agent, on the official Claude Agent SDK — sessions, tool calls, permissions through the policy, client tools over MCP, resume and fork
Official TypeScript SDK, CLI, and MCP Server for Allevitas AI agent platform
AI Agent SDK for AEC project management
Deterministic compiler for AI agent plugin marketplaces: schemas, source parsing, provenance verification, per-harness materialization, and provenance-checked static artifacts.
Freya - Lightweight Microkernel AI Agent System | 轻量级微内核智能体系统
Enterprise-ready AI Agent Engine with multi-provider LLM, memory & tool-calling
Agent Client Protocol adapter for @sigx/ai-agent — every ACP agent (Gemini CLI, Cursor, …) as an Agent, with vendors as presets
Production-grade autonomous AI agent platform optimized for Google Cloud Run, Neon pgvector, and Gemini/Cloudflare
Native C++ AI agent framework with Node.js bindings
The Cordium AI agent that runs inside a Cordium Workspace and manages the User's Workspaces
Shogo Agent — agent-runtime primitives (loop, router, hooks, orchestration) for backends built on pi-ai/pi-agent-core.
TypeScript runtime for LLM agent graphs with bounded loops, live updates, and isolated Git worktrees
TypeSafe AI (Jev) decision-model provider (IDecisionModel) for @mcp-abap-adt/llm-agent.
Janis-ready LLM agent — boots from Janis config, honors takeover, serves hosted channels
Turn a single YAML file into a running LLM agent with an HTTP API. You define the system prompt, model, tools, and safety limits; the service runs the tool-use loop and streams every step back to your client over Server-Sent Events.
Shared TypeScript types for Cogitator
The universal, low-level SDK for Keyframe Labs.
Lightweight, type-safe dependency injection container for TypeScript with constructor injection, factory functions, and lifetime management.
General-purpose agent with transport abstraction, state management, and attachment support
Processing context, message queue, and output normalization
Useful util functions when extending the embedjs ecosystem
TypeScript AI agent runtime. Write your agents in code and choose how predictable they are: deterministic steps where they can be, an LLM only where a step needs judgement, all on your machine.
Self-modifying agent capabilities for Cogitator - tool generation, meta-reasoning, architecture evolution
Session-less LLM wrapper that ships a complete pet (Buddy) AI subsystem: bones (deterministic) + soul (LLM-generated) + stats (event-driven growth) + memory (append-only). CLI (`easbot-buddy`) + MCP server.
Interfaces for extending the embedjs ecosystem
A first-party SecureComs agent. It attaches to the local SecureComs daemon and runs a BYO (bring-your-own) OpenAI-compatible LLM against incoming messages, with skills, per-channel memory, and a local tool gate — no AgentVault backend involved.
Token-lean LangChain agent: intent routing, zero-token tool fast path, RAG with answer caching, per-user token limits and usage for Ollama, OpenAI, Claude, Gemini and OpenRouter. Optional MongoDB storage.
TypeSafe System One integration for LangChain.js (Jev classifier).