Python agents

LangChain integration for the Preference Profile Exchange (PPX).

LlamaIndex integration for the Preference Profile Exchange (PPX).

OpenAI Assistants API integration for the Preference Profile Exchange (PPX).

Standalone AI agent warehouse cost attribution and cap enforcement

Coinbase AgentKit action provider for renting real NVIDIA GPUs on Prism Network.

A teaching-grade agent framework kernel in ~1800 lines: small enough to read in a weekend, structured like a production runtime

Stateful Technical PM Agent — multi-project CLI with persistent per-project context

LangChain integration for the Progress Memory SDK

Redact sensitive data from LLM prompts before sending them to a model.

Catch AI coding agents cheating on their work — verdict on facts, not opinions.

protoAgent — LangGraph + A2A template for spawning protoLabs agents

CrewAI tools for Provision Stack — deploy cloud infrastructure via AI agents.

LangChain tools for Provision Stack — deploy cloud infrastructure via AI agents.

Client helper for ProxyLLM, the OpenAI-compatible LLM gateway: one-line OpenAI client wiring plus the autonomous email-OTP account signup flow.

A practical GUI and Python toolkit for Pixeltable YOLOX

A Pulumi provider to manage Garage S3-compatible object storage.

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

Phone approvals for LangGraph and LangChain agents. Your agent asks, your user taps Approve or Deny.

Phone approvals for OpenAI Agents SDK agents. Your agent asks, your user taps Approve or Deny.

Cancer biology and oncology: driver genes, mutation classification, signaling pathways, clinical trials search, and PWM registry benchmarking.

The official Claude Code agent — same as Anthropic's, full coding toolset. GPU via providers.

The official OpenAI Codex agent — same as OpenAI's, full coding toolset. GPU via providers.

PWM agent runtime (core): the AI4Science harness + pwm_agent_core facade that standalone PWM agent packages run on.

Computational drug design: molecular docking, ADMET prediction, similarity search, lead optimization, and PWM registry benchmarking.

Snapshot/compressive spectral imaging (CASSI): solutions, physics, GPU eval.

Simulated peer review of a paper file → reviews + decision.

PWM Research agent — PWM-grounded scientific research. Standalone or embedded in AI4Science.

General coding assistant — one harness across Claude / ChatGPT / Gemini. No PWM data.

Jason-style AgentSpeak for Python. Fork of niklasf/python-agentspeak, a Python interpreter for the Jason (jason-lang.github.io) agent-oriented programming language.

AI-Native LLM Training & Infrastructure Abstraction Library

Pydantic AI capability for chDB, the in-process ClickHouse engine: analytical SQL tools with engine-level read-only safety and typed engine errors mapped to ModelRetry.

Tool-call error recovery capability for Pydantic AI agents

ProjectGedanken

Open Knowledge Format (OKF) plugin for Pydantic AI

Fast local web viewer for pydantic-ai traces (list[ModelMessage] JSON dumps)

Pydantic AI integration for the UniRate currency-exchange API — a toolset plus tool functions for FX rate lookups, conversion, currency lists, and VAT rates.

Software suite to calculate fragmentomics features from cfDNA and perform downstream analyses.

Large Language Model Instinct Testing under Survival - benchmark LLMs in a hand-built Crafter survival world.

A pytest plugin for evaluating and testing AI agents — record, replay, and assert agent behavior

Pytest plugin for agent-saga: deterministic replay verification, chaos injection, and WAL fixtures.

Pytest plugin that works with pytest-cov to generate coverage data for CircleCI's Smarter Testing

CrewAI integration for qarai-agent-guard that provides runtime security for AI agents through threat detection, policy enforcement, and content protection.

LangChain integration for qarai-agent-guard that provides runtime security for AI agents through threat detection, policy enforcement, and content protection.

Local, compiler-backed optimization agent (QOKit / CUDA-Q)

A native pytest plugin for testing and verifying quantum circuits - Qiskit, Cirq, PennyLane (via OpenQASM), simulators and real hardware.

Agent-safe model read and write tools for Qiaotong bridge software

Local-first evidence substantiation/RAG for Qiro environmental claim review.

Local MCP server exposing QpiAI Quantum SDK tools to agent harnesses

Add your description here

A personal AI model-routing stack that learns from your usage

QuillMQ: a lightweight single-node message broker (work queues, pub/sub, RPC, durable delivery).

Never ship unverified LLM output: multi-model councils, severity-graded audit gates, bounded retries, deterministic fallbacks. Zero dependencies.

High-performance Python library for Minecraft: Bedrock Edition protocol

Reproducible retrieval benchmark: measures RAG design choices against a stated BM25 baseline

Portable RAG for Python projects: ingestion, vector search and sourced answers, with no imposed infrastructure.

rag-assistant — AI Agent

Audit toolkit for retrieval, evaluation, benchmark, and security checks in RAG systems

Composable building blocks for production RAG pipelines, with an auto-tuning evaluation suite.

Find common quality and safety issues in RAG chunks before indexing.

A debugger for RAG applications: diagnoses retrieval, context, and grounding failures.

Lightweight JSONL tracing for debugging failed RAG answers.

RAG indirect prompt injection guard: scan retrieved documents for prompt-injection (instruction override, system/tool-prompt manipulation, exfiltration, invisible-Unicode/homoglyph smuggling) in English and Turkish, and quarantine poisoned docs before they reach the model.

A from-scratch CLI evaluation framework for RAG pipelines.

Read-only staleness/orphan/duplicate/retrievability checks for a single pgvector, Qdrant, or Chroma index.

A pip-installable Python library providing drop-in RAG evaluation capabilities using RAGAS

Bi-temporal RAG platform: cited, temporally-correct answers plus system-time replay. Self-hostable memory and audit layer for AI agents.

Extractive, provenance-preserving context compression for RAG pipelines.

Lightweight semantic cache for LLM and RAG pipelines. One class, one method, zero required dependencies, sync and async.

Ragento Analytics MCP server — ingest, query, and analyze your data from Cursor and agent IDEs

Caching based RAG primitives

A thin, CI-gated evaluation gate for RAG & LLM systems: golden set, LLM-judge (or heuristic) scorers, and band-based quality gates.

AI Coding Agent

ragi — Retrieval that rises. Eval-first, agent-agnostic RAG toolkit -- define, measure, iterate, ship as a portable retrieval contract (Python lib / MCP server) any agent consumes.

Recursively scrapes websites and builds a localized memory context to return specific reference text chunks.

遵循RAG-Storage-Spec的知识库构建工具

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