Python agents

Token-aware, boundary-respecting text/document chunking for RAG ingestion (stdlib-only).

엔터프라이즈 RAG를 위한 범용 문서 전처리 파이프라인 (HWP/PDF/docx/xlsx 지원)

Robustly extract, repair, and coerce structured data (JSON) from messy LLM text output.

A prompt template engine for LLM apps: validated variables, reusable few-shot blocks, and clean chat/message construction.

Detect and reversibly mask PII / secrets in text before sending it to an LLM.

A tiny, dependency-free in-memory vector store for prototyping RAG / semantic search.

A simple, extensible toolkit for building advanced multi-agent Retrieval-Augmented Generation (RAG) pipelines in a few lines of code.

RAGL — a memory-safe, flexible-syntax, AI-native programming language

A lightweight, highly configurable RAG retrieval engine. Framework-free, protocol-driven.

Self-hosted RAG engine: hybrid dense+sparse retrieval, 28-format ingestion (docs, URLs, images, audio, video), 6 vector backends, 8 embedding providers, 12+ generation providers with automatic fallback, query rewriting (HyDE/contextual/multi-query), structured JSON output, real per-call cost tracking, and standalone retrieval via retrieve(). Composable with the optional ragleap-graph package for knowledge-graph-augmented retrieval. BYOK, no vendor lock-in, no hardcoded model defaults.

Build semantic search, multi-provider question answering, and REST APIs over your documents in a few lines of Python.

Regression tests and explainable release gates for RAG and AI agents

Automated search over RAG-pipeline configurations with reusable trial artifacts for training and inference

Document preprocessing toolkit for RAG and LLM pipelines: text cleaning, chunking strategies, metadata extraction, and token counting.

A sage that only speaks from your corpus — a reusable, tenancy-agnostic RAG engine behind ports

Build semantic search, question answering, and FastAPI-powered RAG applications in just a few lines of Python.

A lightweight evaluation and regression detection library for RAG pipelines.

Similarity-graph RAG CLI: index a corpus into a chunk-level embedding graph and query it

Enterprise-grade, local-first RAG for Python

Raven — AI-assisted learning companion. Auto-detect materials, split by chapters, generate quizzes, organize notes.

Fine-tune and serve small LLMs on your laptop

Trustworthy retrieval for an AI agent's own memory — verdict, confidence and provenance per hit, or an explicit abstention

A pluggable memory layer for LLM agents with usage verification, contradiction resolution, and multi-tenant access control

Rein — keep your Claude Code agents lean and in control. Token-lean, stack-aware agentic dev flow.

AI-Powered Codebase Bug & Vulnerability Scanning CLI

Local-first AI code agent in your terminal. Inspired by Claude Code and Codex CLI.

Respan instrumentation plugin for AgentOps

Respan instrumentation plugin for AgentScope

Respan instrumentation plugin for Microsoft Agent Framework

Respan instrumentation plugin for Ragas evaluations and experiments

Respan instrumentation plugin for Microsoft Semantic Kernel

LLM capabilities library for the ResuMesh portfolio and CV builder

Record-replay debugger for AI agent runs

Domain-structured RAG pipeline template

An AI teammate that takes care of your GitHub work.

Prime Agent CLI for RobinAgents — autonomous GTM agents on Robinhood Chain

Persistence ports for Roborean projects and runs

JSON/YAML filesystem persistence for Roborean

SQLAlchemy persistence adapter for Roborean

Robot Framework libraries for testing the agentic stack: MCP servers, Agent Skills, SubAgents, and Hooks - deterministically, with an LLM judge, or with a coding agent.

Adaptive LLM execution engine - intelligent routing, cascading, caching, and budget management

RunAPI Gemini TTS SDK for multi-speaker speech generation in JavaScript, Python, Ruby, Go, Java, and PHP

RunAPI OpenAI TTS SDK for speech generation in JavaScript, Python, Ruby, Go, Java, and PHP

module boilerplate

Python SDK for RustyRAG — fast, minimal RAG-as-a-Service client

Multi-agent orchestration backend — FSM pipeline, workflow engine, and agent bus on one substrate

Name placeholder — not yet released.

Real Algebraic Geometry Library

Minimal tool-calling agent over LiteLLM, tuned for local Ollama models

MCP-native scientific skills for reproducible computational biology and drug-discovery agents.

Local hybrid retrieval and faithfulness benchmark for scientific papers

Research-data storage triage: read-only stat-only scan + referenced-file-aware rotation of versioned build artifacts (e.g. SIF images)

Haystack integration for ScrapeUnblocker - scrape pages behind anti-bot protections

A terminal user interface (TUI) for SDG Agents — powered by local AI models

A small example package

A small example package

Official Search1API tools for LangChain

🛡️ Experimental security guardrails for LangChain agent code execution — Docker sandbox isolation.

LiteLLM adapter for Sefia.

AI-powered multi-agent framework to plan, generate and heal Selenium Python tests (pytest + pytest-bdd)

Sentinel AI — client SDK for AI agent governance & identity. Sign agent actions with Ed25519 and enforce them through the Sentinel authorization gateway. Private beta: [email protected]

CrewAI adapter for Sentinel AI agent governance — wrap any CrewAI tool so every call is authorized (and audited) by the Sentinel gateway before it runs. Private beta: [email protected]

LangChain adapter for Sentinel AI agent governance — wrap any LangChain tool so every call is authorized (and audited) by the Sentinel gateway before it runs. Private beta: [email protected]

AgentKit action provider for SENTINEL — pre-execution transaction safety oracle for autonomous AI agents, paid via x402 on Base

The self-improving AI agent — creates skills from experience, improves them during use, and runs anywhere

Python client for the Server4Agent REST API — sync + async, typed, with retries.

Deterministic Git lifecycle and execution harness for AI-agent work

Hybrid vision web agent — planner + UI-TARS grounder + Playwright

A small example package

A small example package

A small example package

A small example package

Local agent run receipts with signed JSONL records and Markdown review artifacts.

Renamed to silica-harness. This package installs it.

Zero-dependency Python graph runtime for agent loops with Mermaid export

The self-improving AI agent — creates skills from experience, improves them during use, and runs anywhere

LangChain and CrewAI tools for Sirenic - official French & European company data, paid per call via x402 (USDC/EURC on Base). No account, no API key.

Portable skill.json manifests for Agent Skills

Pinned Vulkan llama-server build for Skulk's served GGUF engine (Linux x86_64)

Turns natural-language engineering tasks into validated, sandboxed, auditable workflows - powered by SmartMDAO.

Unofficial smolagents Model adapter for ChatGPT Codex OAuth device-code auth.

TTTPS Proof-of-Time step callback for smolagents: cryptographic audit-trail timestamps for agent step outputs via the public KPP Provenance API

Framework-agnostic agent engine shared by the snowland-aitool cloud web service and the local IDE MCP server.

Hand-written HIP kernels for Qwen3.6-35B-A3B on AMD gfx1151 (Strix Halo)

Compiled HIP kernels for SnowLLM on AMD gfx1151 (Strix Halo)

社交关系AI管家 - 独立 CLI 工具，自动追踪社交关系，帮你拟消息、记待办、维护人脉

Enterprise-grade LLM security guardrail library for protecting input prompts and output responses

General purpose 'deep agent' with sub-agent spawning, todo list capabilities, and mock file system. Built on LangGraph.

Structured thinking as a pluggable layer for any OpenAI-compatible API

Runtime-agnostic governed agent execution — Community Edition

Reusable runtime core for durable agent applications.

Gestor de contexto para agentes IA basado en grafos comprimidos generados desde Markdown

A strict Spec Agent workflow for spec-driven development

Makes any LLM behave like a regular REST API. Define the contract, specllm enforces it.

Spectron agent memory for the OpenAI Agents SDK

Spectron agent memory for Pydantic AI: toolset, auto-recall history processor, and persistence helpers.

Spectron agent memory as tools for the Strands Agents SDK.

Sphinx extension that submits your docs to AgentReady after every build, making them instantly queryable by AI agents via MCP.

Spidy — A sharp, friendly terminal AI assistant. Cross-platform CLI powered by NVIDIA NIM & Ollama.

Anthropomorphic psychology engine built on SPL Pure Core V8.0 — deterministic emotion, trauma, memory, trust, and defense mechanisms.