Python agents

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

Sphinx extension to make documentation LLM-friendly

SQL Storgage Middleware for SQLite and Postgres

Open-source execution authorization and control infrastructure for AI agents

A reliability layer for LLM API calls: retries, rate limiting, validation, tool calling, fallbacks, and structured logging.

PyO3 bindings for the Rust CoreLoop.

A Python wrapper for Stegstr CLI, allowing AI agents to easily hide and transfer secret data in images.

基于 Boto3 与 aioboto3 的进程内对象存储客户端

Portable, auditable, cross-vendor memory for LLM agents: evidence-bound claims, trust tiers, and compiled context views.

An MCP which adds terminal capabilities to an agent.

The record of what an AI agent did, for whom and with whose approval; plus the library a tool server needs.

Run before you buy on Robinhood Chain. A client for the Swarm0x api and its MCP tools: simulated checks, holders, transactions run before they are signed, trades written for your own wallet.

OAuth 2.1 for autonomous AI agent swarms: signed, short-lived, capability-scoped delegation tokens.

Stock swing attribution — detects unusual moves and explains them, or abstains

A shared coordination board for AI coding agents driven by different people

SynapseRAG — an embeddable, zero-external-dependency Tri-Brain RAG engine (Dense/Late-Interaction + Neuro-Associative Graph + Sparse Lexical).

Tab Agent Python SDK：Tab + Agent/Run，覆盖 Open API 与 A2A。

Keep your agent skills deployed identically to Claude Code and Codex from one manifest, and audit projects so either agent sees the same instructions, skills and hooks.

Microsoft Agent Framework adapter for Taisce: a context provider that injects governed memory as one untrusted user message and records the turn afterwards.

LangGraph adapter for Taisce: agent middleware that injects governed memory as one untrusted human message and records the turn afterwards.

Safe writes to Tally Prime for AI agents — refuses any name Tally does not already hold, and reads every voucher back to prove what was stored.

Async LLM task library and bot service for Taranis AI

Temporal-native agent harness (experimental) — durable agents on Temporal, with the AI SDKs you already use.

Temporal integration for the OpenAI Agents SDK (temporalio.openai_agents)

An MCP server that provides terminal capabilities to AI agents.

Browser terminal deck: persistent named terminals, a Monaco file viewer, and automatic claude/codex session resume across restarts.

Autonomous terminal-based coding agent designed around verifiable software changes. Build. Verify. Ship.

A typed Python wrapper for Terragrunt, OpenTofu, and Terraform executables.

TESSERA — Temporal Evolving State Synthesis with Explicit Relations and Atomic Memories: a text-first, auditable memory and evidence layer for AI agents.

AI-assisted HWPX thesis citation and reference validation

A production-grade, terminal-based AI/Agentic coding harness with enhanced security

Tinet Agent CLI Orchestrator

Official Python SDK & CLI for TitanRAG Enterprise Platform

Local visual editor for tketool Pipeline Graphs

MCP server that lets any AI agent launch, watch and steer coding agents (Claude Code, Codex, Hermes, aider, ...) running in tmux panes.

Claude Agent SDK adapter for ToolBroker.

CrewAI adapter for ToolBroker.

Replay AI agent failures locally and turn them into regression tests.

Opt-in vLLM scheduling-context export for TraceLoom AugDB

Connect a locally run TradingAgents analysis to your Investboard account

Vectorless RAG: tree + hash addressing with structural query resolution and a BM25 fallback, instead of one embedding per chunk. Zero required dependencies. Domain packs for medical, finance, and education.

Real-time safety supervisor for LLMs — flag a response or abort a stream mid-generation, powered by TypeSafe's Jev.

An LLM-agent evaluation harness that proves an agent is broken when its outputs look fine.

Verify an AgentCert + TrustScore inside a Python MCP server (shadow mode, opt-in, dependency-free).

Highly optimized distributed training for diffusion language models.

Google Cloud integrations for Twilio Agent Connect (TAC) - connectors for Google Cloud agent runtimes

Type-Safe Decoding for Autoregressive LLMs

LLM observability and resilience decorator — semantic prompt caching, automatic retries, rate limiting, cost tracking, and a local web dashboard for any Python LLM call.

A unified async interface for multiple LLM providers (OpenAI, Ollama, OpenRouter) with event-based streaming, reasoning support, and multimodal inputs.

An MCP server that gives AI agents controlled terminal capabilities.

Agent-pipeline adapter for v8unpack: path factory, FormArtifact, drift index

LLM API security auditor — prompt injection, jailbreak, ASCII smuggling, data exfiltration, OWASP LLM Top 10 mapping

Durable Vantage lifecycle callback for LiteLLM

Deterministic guardrail, SIEM audit exporter, and subprocess firewall for autonomous AI agents

TriAttention KV-cache compression plugin for vLLM Ascend

Fail-closed runtime support for versioned Ascend quantized model artifacts

Runtime-loadable INT8 KV-cache attention backend for vLLM-Ascend-HUST

vLLM-HUST plugin carriers for vllm-ascend: decode FIA de-mask, RoPE variant fixes, zero-cost wiring, MLP chunking and inert split-batch planning

Modular graph and replay optimizations for vLLM Ascend

A high-throughput and memory-efficient inference and serving engine for LLMs

BidKV — CompressionBid protocol layer for KV cache scheduling primitives

Migration package for OPset, the vLLM-HUST operator optimization bundle

Pluggable kernel replacements and operator fusions for the vLLM-HUST Ascend backend

Zero-copy CUDA/MACA IPC weight pre-load cache for vLLM instant restart

Reusable voice agent sessions with local speech and OpenRouter adapters

An open-source, provider-agnostic realtime voice agent framework in Python

Volcengine llmscan SDK for Python

Volcengine llmshield SDK for Python

A fail-closed gateway between an AI agent and its tools: normalize, default-deny policy, human approval, append-only audit.

A client for the WhatsApp Agent Platform: send, receive, media and transcription, as a library and a command.

First-class markdown twins, optional authored `/llms.txt`

Azure virtual machines plugin for Waldur Site Agent

Shared LDAP client for Waldur Site Agent plugins

LDAP role-driven group membership sync plugin for Waldur Site Agent

Python SDK for Warpswarm: on-demand human judgment for AI evaluation and labeling.

A least-privilege controller for local coding agents

Analyze coverage in Wazuh JSON archives using DuckDB

国产大模型路由 MCP 连接器（11 个路由/对比工具）

多智能体编排 MCP 连接器（DAG 流水线编排）

WebGIS, GIS, GeoAI and spatial engineering skills plus Python GIS runtime extras.

Reusable multi-provider AI agents for web development across local projects

Weft — a RAG engine built as a microkernel. The default install: the kernel's packs, and the weft command.

Wellmanifest unified standards runtime — policy-as-code checker for all wellmanifest standards

Propose-only priority documents, deterministic ranking, and conformance contracts

A simple Python library for the WhatsApp Agent Platform API

Python SDK and MCP server for the WhatsApp Agent Platform

Workspace Intelligence Agent (WIA) — Graph-grounded workspace intelligence platform for code understanding, AST parsing, flow tracing, and RAG Q&A

Daily work log and token report across Claude Code accounts and devices, plus imported claude.ai chats, synced through your own private git repo

One endpoint for any agent capability: resolve a task, route it to the best provider, pay per call in USDC over x402.

Pay-per-call AI Agent Tools (Web Reader, Search, JSON Extractor, CAPTCHA solver) with automated x402 Base USDC micropayments

Python SDK for xAgentGuard AI Agent Governance and Enforcement Proxy

Agentic X/Twitter thread content & media harvester for AI agents — no login, no API keys, no browser. MCP wrapper included.

An autonomous mini LLM agent with tooling.

A package to prevent Dependency Confusion attacks against Yandex.

Agent hosting for the ygo74 agent runtime: endpoints, discovery, sessions and human approval

MCP server hosting for the ygo74 agent runtime: transport, authentication and health

Security and authentication foundation of the ygo74 agent runtime