Python agents

Hook any production agent. Ship extensibility without a fork.

MCP server for SEC financial report download, parsing and search

Swink™ AgentShore™ — RL-based multi-agent orchestrator

Agentto SDK — Intelligent Execution Engine for AI Agents

Artemis LLM Benchmark — correctness validation and performance benchmarking for any OpenAI-compatible LLM serving endpoint

A modular framework for evaluating and verifying agentic LLM outputs.

Python SDK for Bedrock.

Python SDK for Bedrock Agent.

Python SDK for Bedrock Agent Runtime.

Python SDK for Bedrock Agentcore.

Python SDK for Bedrock Agentcore Control.

Python SDK for Bedrock Data Automation.

Python SDK for Bedrock Data Automation Runtime.

Serve CARL reasoning chains as HTTP agents (FastAPI) — per-agent Swagger, hub with hot-reload from gigaevo Memory

Reserved. Not for public use yet.

Coordinate multiple AI coding-agent sessions in one repo: file locks, task board, presence, and messaging over shared SQLite. Claude Code skill + hooks included.

A shared message and state bus for multiple Claude Code sessions

Claude Sandbox SDK — 管理 Claude Agent 沙盒服务的 CLI 工具

Ethan — Lightweight personal AI agent with memory, skills, and multi-model support

Folder-based connector for eTiKeT sync agent

Native filesystem connector for eTiKeT sync agent

QCoDeS connector for eTiKeT sync agent

File converters for eTiKeT sync agent

Placeholder to reserve the FreeSDN agent package name (on-site network discovery daemon). Official release coming soon. See https://freesdn.org

Break your agent before your users do. Adversarial stress-testing and regression suites for AI agents.

Go Hare Python SDK for Claude Code

Google-OAuth-gated LLM gateway: verify a Google ID token, then run a Gemini (Vertex AI) completion for the verified caller.

Run a prompt through a LangChain (system + human) chain over Gemini on Vertex AI; optional LangSmith tracing.

Turn a prompt + a field schema into validated, typed JSON (Instructor over Gemini 2.5 Flash on Vertex AI).

GPT Image 2 generation and editing through the Polza API

Production LLM calls. Just the three lines. Reliability, native caching, and reversible context compression on by default.

Lag: Lamin's Agent CLI.

LangChain integration for the Unison Brain — memory, chat history, and retriever

Bidirectional, drift-detecting sync between a LangGraph/LangChain graph's topology and a Mermaid stateDiagram-v2 contract.

LeviathanTalon: hierarchical Kabbalistic multi-agent swarm orchestrator. 2,832 concurrent agents at full scale.

LlamaIndex memory provider backed by the Unison brain — long-term agent memory via a knowledge graph.

LLM Batch Inference

Run Claude Code (and other LLM CLIs) inside a Docker sandbox, against a switchable local or remote LLM endpoint.

LLM Guard Rails - An actively maintained security toolkit for Large Language Model interactions. Features advanced sanitization, harmful language detection, data leakage prevention, and prompt injection resistance with continuous improvements and enhancements.

A tiny, dependency-free tool belt for LLMs: token counting, cost estimation, retries, prompt templates, and text chunking.

pprof for your LLM context - see where every token and dollar goes.

Context compression and planning for RAG and AI agents: fit retrieved documents, chat history and tool output into a token budget.

Coordination certificate for multi-agent (LangGraph) systems: prove your agent graph is deterministic, deadlock-free, loop-aware, optimally scheduled, and retry-safe — static analysis, CI-ready.

Agent skills package manager — thin pip wrapper for the lore binary

Mimir persistent memory tool for CrewAI agents

Mimir persistent memory backend for LangGraph agents

AutoGen v0.4 MemoryStore adapter for the Mnemosyne memory substrate. Implements the MemoryStore protocol with per-agent container scoping, hybrid BM25+vector recall, async support for high-throughput multi-agent runs.

CrewAI long-term memory adapter for the Mnemosyne memory substrate. Implements the LongTermMemory protocol via duck typing, with per-agent and per-task scoping, hybrid BM25+vector recall, idempotent writes.

OpenAI Agents SDK lifecycle hooks for the Mnemosyne memory substrate. on_turn_start, on_turn_end, search, and store hooks backed by the substrate, container-scoped, with automatic redaction.

Command-line client for SimpleAgent deployments

Pair-wise ELO evaluation arena for local LLMs.

A desktop GUI application for text classification using LLMs (Ollama, vLLM, SGLang, llama.cpp)

Ontology-guided knowledge graphs and graph-grounded RAG for document intelligence

Agent-based extraction framework for transforming parsed documents into structured planogram data

Prompt-level analytics for Claude Code — tokens, costs, and session insights from your local JSONL files

Run any agent (Claude, Codex, custom) on any machine — with no API key on the machine. A secure, self-hosted proxy for models and tools.

CI/CD-integrated RAG evaluation pipeline — quality gate for AI chatbots using Ragas + Groq LLM judge

RAGObserve: local-first observability, debugging and evaluation for RAG systems. The MLflow for RAG.

Configuration-driven RAG MCP server: ingest, watch, index, and search arbitrary knowledge sources behind a stable MCP tool surface.

Agent code generation from YAML contracts

Meta-agent and runtime client for TellMesh hypervisor

Haystack integration for SearchApi Web Search

Per-node management plane for the Seren cluster - manifest-driven service lifecycle, status, and orchestration.

SDK for using LLM

Self-Learning Index Memory for AI agents

Local AI compute control plane for Claude Code and coding agents. Route subagents across your Macs, GPUs, and Ollama nodes — with real-time fleet health, role-based routing, model warmup, and execution tracing.

Set up retrieval-augmented generation from your own text in one call. Pass your documents and a model, and get a RAG-backed LLM.

TellMesh — URI-first agent monorepo umbrella (uri3, nl2uri, hypervisor, agent factory)

A lightweight, trainable language model SDK

AI agent observability SDK for agencies

Two LLMs enter. One verdict leaves.

Minimalist coding agent harness with a Textual TUI and headless CLI. Native vtx event loop. <1k-token system prompt, 50+ LLM providers, AGENTS.md + skills context, session tree, prompt/auto permissions.

Free, open-source, async-first web scraping toolkit for LLM agents

A server-side browser proxy that lets clients operate websites without direct remote connections.

AWS Bedrock Agents governance middleware for Aegis ACP (maintenance-only — Anthropic SDK is the active hero)

Never lose work when an agent fails.

Shared operational memory and coordination for mixed AI agent fleets.

Lightweight AI agent framework with tool use, ReAct reasoning, multi-agent teams, and memory.

Decentralized agent-to-agent communication — publish results, wait for peers, no broker required

A lightweight, auditable agent workflow for document-grounded PDF generation and rubric-based evaluation

A rendering convention for AI agents — append /agents to any FastAPI route and get a fully structured agent workspace with state, capabilities, RBAC, and navigation.

Runtime policy control plane for production AI agents. Block, degrade, escalate — without a redeploy.

Discover, version, and deploy production AI agents — the registry for your agent fleet

Alibaba Cloud AgentLoop (20260520) SDK Library for Python

Arbor — an autonomous research agent that proposes ideas, edits code, runs experiments, and iterates on a hypothesis tree.

Autourgos LLM wrapper for the OpenAI Chat Completions API

Self-contained ReAct (Reasoning + Acting) agent for the Autourgos framework — works with any OpenAI-compatible LLM

One-line spending control for AI agents. @budget(max_usd=10.00) decorator for LLM APIs and x402 payments.

Forecast which agent calls burn Anthropic Claude Agent SDK credit after the 2026-06-15 billing change — Claude Code / claude-code-action / claude -p cost, monthly risk, and cheaper alternatives.

计算巢Agent部署集成库，基于 Google ADK 架构对接云上 Agent 能力

Haystack integration for datadog

agents-server — Python SDK for building AI agent services

Counterfactual evaluation toolkit for RAG systems

PostgreSQL storage backend for fast-feature (asyncpg).

Async SQLAlchemy storage backend for fast-feature (shared by the SQL drivers).

First-Class Hermes Tool Agent — Offline ReAct agent with dual memory (episodic + semantic), skill learning, and daemon mode

ICONOCLAST — Discriminative representation editing for open-weight LLMs. Beats HERETIC baseline across all tested models.

LangChain integration for rezunate-llm-sdk

Read-only LangChain tools for RustChain — let any agent query the hardware-attested agent economy.

Shrink LLM context windows by removing noise, redundancy, and long-tail detail — without losing signal.