Python agents

Compatibility launcher for the canonical PlatformIO MCP engine

PlatformIO MCP and CLI with a bundled Node runtime

Private language model inference with a local Responses API and remote matrix execution

Ultra-lightweight, browser-less static image exporter for Plotly

Inference engine for large language models on consumer GPUs with deep optimization for older hardware

Anthropic plugin for PolyLLM.

PolyLLM Python core: unified protocol, registry, and parameter policy.

DeepSeek plugin for PolyLLM.

OpenAI plugin for PolyLLM.

OpenAI-compatible endpoint plugin for PolyLLM.

Selective Instruction Routing (SIR) for Large Language Models

Locally-hosted LLM-based PR review agent with enforced usage budgets

Govern Claude Agent SDK tool use through Primary Path (canUseTool gate)

Govern LangGraph interrupt()-based HITL through Primary Path

Govern OpenAI Agents SDK tool approvals through Primary Path

A reversible redaction layer for any LLM connection

An open-source AI agent for evidence-backed project risk intelligence.

Self-hosted MCP memory for AI agents with evidence-backed, explainable claims

Fast, dependency-light Telegram Bot API framework built on urllib3

Phone approvals for Haystack agents. Your agent asks, your user taps Approve or Deny.

Phone approvals for Pydantic AI agents. Your agent asks, your user taps Approve or Deny.

A lightweight local workflow orchestrator for development and review agents.

Pure Python Minecraft Bedrock Edition bot and networking library

A minimal, type-safe Python library for LLM chat completions with OpenAI, Azure OpenAI and Codex

Python library wrapping the Claude Code CLI: prompts, background agents, auth, MCP, plugins, and more

Pydantic AI toolset and capability giving agents a real email inbox with Atomic Mail

Azure Cosmos DB MemoryStore for the PydanticAI harness Memory capability — CAS versions via ETags and idempotent operation receipts

Amazon DynamoDB MemoryStore for the PydanticAI harness Memory capability — CAS versions and idempotent operation receipts via conditional writes

Escalate a Pydantic AI agent to a stronger model when output validation keeps failing.

Shared core for PydanticAI harness MemoryStore backends — CAS versions, idempotent operation receipts and bounded search over a few conditional primitives

Pydantic AI Harness MemoryStore and Pixeltable catalog tools.

PostgreSQL MemoryStore for the PydanticAI harness Memory capability — the upstream transactional store, built from a connection URL with an owned asyncpg pool

Record and replay LLM HTTP traffic for deterministic pytest runs

A minimal three-layer guardrails template for AI coding agents in Python projects.

An experimental open-source framework for metadata-aware, inspectable, constrained AI-assisted analysis over structured data.

pyTracer adapter for AutoGen - capture agent runs via an OpenTelemetry exporter.

pyTracer adapter for CrewAI - auto-instrument crews via the event bus.

pyTracer adapter for LangGraph / LangChain - auto-instrument agents via a callback handler.

pyTracer adapter for the OpenAI Agents SDK - auto-instrument agents via a tracing processor.

编码 agent 框架:单 agent core + 扩展(MCP / 多 agent / web)

QuadKit quadkit-ai-agents — reserved namespace

QuadKit quadkit-ai-llm — reserved namespace

QuadKit quadkit-ai-rag — reserved namespace

Unified blob storage abstraction for Quadkit Framework - S3, GCS, Azure Blob, and local filesystem

R2Flow RPA agent - runs on Windows machines and executes processes dispatched by a r2flow-cloud orchestrator

rag-aio: asynchronous, modular RAG platform — facade, CLI, and all rag-aio packages in one distribution

A product-neutral contract and conformance kit for treating RAG pipelines as black boxes.

Find and fix gaps in your RAG knowledge base

Score any RAG pipeline: retrieval precision + answer faithfulness

A lightweight document ingestion component for RAG pipelines.

Inspectable context selection for existing RAG pipelines, powered by Jev.

6 RAG recipes, ladder-first: BM25 full-text, LLM query rewriting, hybrid retrieval on SQLite FTS5

Generic observability framework for RAG applications

Deterministic, unit-aware structured-claim verification for RAG systems.

A hybrid retrieval component for RAG pipelines.

RAG Configuration Adviser — rule-based recommendations for building RAG systems

RAGAS-style RAG evaluation with JEV as the primary judge

Stage-by-stage diagnostics for RAG pipelines: builds its own eval set, scores retrieval, ranking and generation separately, and tells you which stage is the bottleneck.

Personal, local-first RAG over your own sources. Desktop-lightweight, desktop-first, and it publishes its retrieval numbers.

RagFabric: self hosted, measurement first RAG platform. Installs the engine, the API and the ragfabric command.

RagFabric engine: retrieval strategies, providers, stores, ingestion, evaluation, access policy.

Python client for a RagFabric server.

RagFabric HTTP API (FastAPI).

MCP server for ragfaith: live faithfulness checks for RAG answers

Universal OpenAI-compatible sidecar proxy with a live ragfaith faithfulness cascade

A modular, extensible Python framework for building Retrieval-Augmented Generation (RAG) pipelines

A modular, production-oriented Retrieval-Augmented Generation (RAG) library.

Prometheus/Grafana/Loki/AlertManager observability Helm chart for RagLeap Core; the changelog states exactly what each release verified

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.

Lightweight tracing for RAG pipelines

Framework-agnostic RAG evaluation: zero lock-in, zero forced API cost.

This name has been reserved using Reserver

This name has been reserved using Reserver

Retriever-agnostic post-retrieval refinement for RAG candidates

Regression-testing and evaluation tool for RAG systems ('pytest for RAG')

Add your description here

Typed Python SDK for the Ragwell managed retrieval API

Synthetic product search relevance and ranking agent

Finds the coverage gates in your repo that can never fail a build (bundled Node.js runtime)

Resume LangGraph agents from their own records, backed by Recall by Polign

Python Client SDK for Redis AgentPlaybooks

Reeflex governance seat for an LLM gateway: a LiteLLM post-call guardrail that rules on every tool call the models behind the proxy propose (allow/deny/require_approval), fail-closed -- one integration for every agent behind the gateway.

Dead-simple regression testing for LLM prompts, built for CI

A small, inspectable runtime for durable agent tool execution, recovery, cancellation, and evidence.

A reproducibility linter, experiment recorder, lockfile system, and drift detector for LLM research.

Self-contained Spec Circuit Requirements Agent (CLI + Textual TUI)

RunAPI GPT Image 2.5 SDK for text-to-image and image editing workflows in JavaScript, Python, Ruby, Go, Java, and PHP

Persistent visual control sessions for external programming agents

sbml2cellml converts between SBML and CellML.

A simple high-level AI toolkit with scratch-trained LLM, image, video, and TTS models plus easy pretrained wrappers.

Placeholder: name reserved by Google. This distribution contains no code.

Placeholder: name reserved by Google. This distribution contains no code.

Open-source SEO agent for link building. Plans campaigns and builds backlinks from Claude, Cursor or Codex via MCP. 1,141-site library.

`cmd??` — instant, man-page-grounded cheat sheets for shell commands, expandable into an agentic chat

Reserved name. The real 'shield-storage' is a private BlackShield package and is not distributed on PyPI.

A small example package

Local-first terminal companion agent (Ollama-powered)

Discover existing community skills and merge the best into one tailored, security-scanned skill set.

Slim, fast, persistent memory + retrieval for LLM apps. numpy + httpx, ~1000 LOC, drops into anything.

Adaptive neural networks for small nonlinear data, with calibrated conformal intervals.