Python agents

Easy data distillation of LLMs for text classification, information extraction, and open-ended tasks

Self-contained, general-purpose LLM agent for the Autourgos framework — works with any OpenAI-compatible LLM

A CLI coding agent with full observability, multi-model support, and security guardrails

The Babel that lets AI agents understand each other: a neutral layer where heterogeneous agents (callables, HTTP/OpenAPI, MCP, framework agents, LLMs) share one interface, collaborate (A2A), and get graded at each hop.

Report line coverage from lcov.info (produced by grcov or cargo-tarpaulin)

MemorySync reference architecture for AWS Bedrock agents: a memory-augmented Converse loop and a Bedrock Agents action-group Lambda — the first vendor action-group memory integration.

Official Python SDK for Blazing Agents

Agent integrations for CapSolver — framework-agnostic tool definitions + LangChain tools.

Thin HTTP client for the RAG debugging/eval platform — register an external RAG, upload datasets, run experiments, fetch results.

A first-principles evaluation framework for LLM agents based on causal invariants, state transitions, and counterfactuals.

Cryptographic runtime receipts for Microsoft AutoGen agents — signed Ed25519 audit evidence for every tool call.

Cryptographic runtime receipts for CrewAI agents — signed Ed25519 audit evidence for every tool call. CCS (Correctover Conformance Shape) L1 + behavior receipts with pre-admission guardrails.

Cryptographic runtime receipts for LangChain/LangGraph agents — signed Ed25519 audit evidence for every tool call.

Cryptographic runtime receipts for LlamaIndex agents — signed Ed25519 audit evidence for every tool call.

Cryptographic runtime receipts for OpenAI Agents SDK — signed Ed25519 audit evidence for every tool call.

Cryptographic runtime receipts for Pydantic AI agents — signed Ed25519 audit evidence for every tool call. CCS (Correctover Conformance Shape) L1 + behavior receipts.

MCP server for the OpenAI Ads Advertiser API, with retries, response budgeting and postcode-level location lookup

Unofficial ChatGPT website client for Python.

Reserved name. Cirrus Networks internal package — not distributed on PyPI.

Reserved name. Cirrus Networks internal package — not distributed on PyPI.

Save, restore and manage Claude Code sessions as workspaces. Windows Terminal native.

Show your Claude Code sessions on an iDotMatrix LED panel.

Claude Code limits and reset times in the macOS menu bar

Log in to Claude.ai without touching your inbox: magic links auto-open in the right browser via IMAP IDLE

Select OpenRouter models directly inside Claude Code

macOS menu bar app showing what every Claude Code session is working on — local and over SSH — in real time

Local, automatic memory for Claude Code. Remembers past sessions in 0.7s for ~2.5k tokens instead of 211k. Nothing leaves your machine.

Cost and prompt-cache diagnostics for Claude Code session transcripts

Install, select, back up and restore complete claude setups.

Claude.ai RE Client v4 — CLI client, session manager, and autonomous coding agent.

CNB Issue 智能体记忆系统（cnb-agentic-memory）是基于 CNB 平台构建的通用记忆工具，把 CNB 的 issue、知识库、检索能力组合成一个开箱即用的智能体记忆层。

Token-efficient, structure-aware Code Intelligence + RAG for private source repositories.

Measure cumulative Codex agent runtime without decoding conversation content.

The reference software engineering harness and runtime for autonomous coding agents.

Haystack components for Context.dev live web search, scraping, and crawling

LangChain BaseMemory adapter for Context-M — the Universal Neuro-Symbolic Memory Fabric.

Verifiable semantic recovery layer for long-running AI agents.

Honest human-in-the-loop consent for AI coding agents: you sign the real argv, not the agent's story. Skill census, MCP sampling deny, inbound fence, and a hash-chained receipt of every approval.

CrewAI tools for Cracked, the agent tool router: discover/inspect/run/run_capability plus cracked_tools(query) that turns discover results into tools.

LangChain tools for Cracked, the agent tool router: CrackedTool plus cracked_tools(query) that turns discover results into StructuredTools.

OpenAI Agents SDK function tools for Cracked, the agent tool router.

Pydantic AI tools for Cracked, the agent tool router: load_cracked_tools() gives an agent 67,000+ tools behind one key, priced per call.

CrewAI tools for Cracked, the agent tool router: load_cracked_tools() gives a crew 50,000+ tools behind one key.

LangChain tools for Cracked, the agent tool router: load_cracked_tools() gives an agent 50,000+ tools behind one key.

LlamaIndex FunctionTools for Cracked, the agent tool router: load_cracked_tools() gives an agent 50,000+ tools behind one key.

CrewAI tools for StackResolve: find, compare, and audit software for AI agents, plus structured company research.

crewAI tools for U.CASH agent monetization over HTTP-402.

Crowe Agent Kernel — the one provider-agnostic agent loop the Crowe ecosystem mounts.

Local MCP tools for checking artifacts, claims, and citations

Local MCP tools for completion contracts and release receipts

Drasi extension for Dapr Agents

A simple multi-user Retrieval-Augmented Generation (RAG) framework for Python.

The Privacy-First AI Database Copilot, Schema Graph Introspector & Post-Commit Recovery Engine (CLI)

An interface for SSH agent socket providers, which expose an abstract communication channel for an SSH agent to derivepassphrase.

Verification-first multi-vendor commissioning control plane with flexible guided customer-file intake, deterministic source/evidence authority, exact-Twin lineage, regression, FAT reporting, and pre-site readiness.

Anthropic target and judges for digline: prompt file in, priced Response out.

Amazon Bedrock target and judges for digline, on the Converse API.

OpenAI target and judges for digline, at any OpenAI-compatible endpoint.

Open-source framework for building agent configurations, testing AI agents, and comparing reproducible AI-system observations.

DK Agent OS — Autonomous Developer Runtime & Commercial SDK Platform

Reusable cross-conversation profile memory for DlightRAG

Drogon C++ backend Claude Code plugin - rules & code generation skills, plus a CLI installer (install/verify/uninstall)

Runtime-neutral dual-agent collaboration orchestrator: architect, coder, tester, reviewer with structured packets and an append-only ledger.

MCP gateway for AI agents to dYdX v4: market data, funding heatmap, TA, verified trader analytics (deposit-adjusted PnL), leaderboards, anomaly & liquidation-cascade detectors. Analytics-only: no trading tools, no keys.

Real-time AI agent bridge for Microsoft Edge using active browser sessions, CDP hardware events, and WebSockets.

The verifying analysis runtime for elbi: an LLM loop that cannot report an effect it has not verified.

A non-hardened implementation of the SSH agent protocol, for use in testing.

Fast, reversible tool calls for LLM agents. Your tools, strapped on, ready before you reach for them.

FinanceGPT Intelligence Cloud API and MCP client

Predict GPU VRAM requirements for LLM training before you start — model weights, LoRA/QLoRA, optimizer states, gradients, activations, and Flash Attention, checked against real GPUs.

Work with Flyte 2. Deploy Flyte on AWS or kind, author and run workflows, apps, agents, data, and ML workloads with the SDK, and operate your cluster through bundled MCP servers.

Run Fortel machine-learning jobs on your own machine.

Run coding agents on Fountain, with real computers, repositories, and credentials.

FshStorage API Wrapper written in Python

Goal-driven FSQ automated testing agent built around OpenAI Agents SDK, Azure OpenAI, harness actions, local utilities, observation, and reporting.

funllmchat

Per-IP semantic similarity rate limiter for GATRAG query endpoints

Bidirectional Model Context Protocol (MCP) bridge connecting Google Gemini Spark with DeepMind Antigravity

Production-grade Gemini API key rotation with cooldown, exponential backoff, RPM tracking, and persistent stats.

CLI and Python API to transcribe videos longer than 30 minutes with gemini-3.5-transcribe while mitigating free-tier 429 errors

Add your description here

Your local AI agent. Runs on basically any hardware — auto-setup, GPU-accelerated, zero cloud, zero API keys.

Buyer-side Python client for the GongYou Agent Market.

Google Cloud Agent Platform Client Library

JWT-gated LLM gateway: authenticate (bcrypt/JWT), then run a LangChain-on-Vertex Gemini completion. Unauthenticated calls are rejected.

JWT-gated LLM gateway: authenticate (bcrypt/JWT), then run a LangChain-on-Vertex Gemini completion. Unauthenticated calls are rejected.

JWT-gated LLM gateway: authenticate (bcrypt/JWT), then run a LangChain-on-Vertex Gemini completion. Unauthenticated calls are rejected.

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

A policy enforcement layer between AI agents and the infrastructure they act on.

Graph RAG knowledge base for coding agents, backed by Neo4j and exposed over MCP

G-spark / HUB Agent tools: CLI + MCP for /v1 API

Hamster: a lightweight CLI software engineering agent powered by OpenRouter.

Python SDK and CLI for the Haystack Enterprise Platform

Haze -- pool your own machines into a private compute network

Search, download, and import HuggingFace GGUF models into Ollama

A Python automation library for easily creating, editing, and extracting data from HWPX (Hangul Word Processor XML) documents.

Native Ollama integration for Hyle.

Universal contracts and infrastructure wrapper for the iagent Mesh — typed predicate registration, transport auth, and per-caller identity for mesh tools

LangChain integration tool for x402 payment-gated web scraping micro-services.

LangGraph tracing for Databricks MLflow