Python agents

Lint your Claude Code skills: descriptions that never trigger, silent frontmatter typos, boot-token cost.

Control an existing interactive Claude Code session from Telegram.

An MCP server exposing a fit-first, honesty-enforced job-application pipeline as typed tools for LLM agents.

Perseus Vault long-term memory as CrewAI tools — local-first, encrypted, persistent memory the agent can explicitly call.

Factory to create Deep Agents (LangChain) specialized on different databases (MySQL, Postgres, MongoDB, Neo4j, SQLite, DuckDB).

Fast Ball Mapper construction with BallTree and optional FAISS backends

FurlPay tools for LangChain — stablecoin payments, investing, and x402 agentic payment rails

FurlPay tools for LlamaIndex — stablecoin payments, investing, and x402 agentic payment rails

Google-OAuth-gated LLM gateway: verify a Google ID token, then run a Gemini (Vertex AI) completion for the verified caller.

Makes a second request to the LLM, asking it if its original response was relevant to the prompt.

A read-only Kubernetes natural-language CLI agent using LangGraph

Perseus Vault persistent, local, encrypted memory for LangChain — tools and a retriever backed by the Perseus Vault MCP engine.

Grafomem (Fair Source) adapter for LangGraph Checkpointers

LeAgents — agentic orchestration for the LeRobot pipeline: collect -> train -> eval -> improve

Lightweight web admin panel for llama.cpp server management

The intelligent context management framework for LLM applications.

Production-grade RAG + multi-LLM framework — hybrid search, streaming, cross-encoder reranking, and a REST API

Publication-quality LLM architecture diagrams, fact sheets, and diffs from HuggingFace config.json — no weights needed

Run coding agents and only mark work done when independent checks pass.

Mathieu Group M23 Weight Initialization for PyTorch Transformers and LLMs

Document conversion agent that watches folders, converts files with marker-pdf, and routes Markdown outputs.

Framework-neutral Odoo connector tools for AI agent runtimes

Local-first DOCX formatter for academic papers with a content-fingerprint guard that proves the text was left untouched — only the formatting changed.

Local-first, encrypted persistent memory for Haystack 2.x pipelines — backed by Perseus Vault.

Perseus Vault persistent, local, encrypted memory for Pydantic AI agents — exposed as a Toolset.

An autonomous, multi-turn AI debugging agent built from scratch using AST surgery.

RAG observability: capture, evaluate, and explain pipeline runs (umbrella package + analyst CLI)

Pipeline instrumentation SDK for ragradar observability system

Shared schema, store, and target parsing for the ragradar observability system

Evaluation layer for ragradar observability system

A unified contract layer for LLM agents — declarative, parameterizable contract templates enforced by deterministic checks and LLM judgment.

Reeflex adapter for Claude Code: a PreToolUse hook that gates every tool call on its impact before it runs (allow/hold/deny), fail-closed -- governance that protects you from your own agent.

Safely run AI agents in Docker to control scientific experiments via MCP

SightRAG: Image and Video RAG. See. Search. Retrieve. Track.

LLM facade Django app for the Stapel framework

Agents that remember: memory-first agent & RAG framework with zero required dependencies.

Improving Zero-Shot Detection of LLM-Generated Content With Token Repetition

Local auth-code challenge plugin for uv-agent.

shared rbac evaluator + cache for the 3tears platform: groups, roles, role assignments, evaluation trails

unified audit envelope, fire-and-forget publish helper, and the audit erasure rule and hub anonymization request for the 3tears platform

Three-tier LangGraph checkpoint saver: L1 SQLite -> L2 NATS KV -> L3 PostgreSQL

Always-on containerized dev environment for AI coding agents, driven over SSH+tmux.

agent-hotwash — analyze coding-agent traces to surface improvement opportunities and bad patterns

An MCP which adds terminal capabilities to an agent

An MCP which adds terminal capabilities to an agent

Map every AI API call in a codebase — offline, no LLM, no keys. Opens a webpage of your providers, models, and agents.

Reusable AI Agent library with RAG, streaming, and long-term memory

Norm-Native Agent SDK — Situation + Runtime loop over EDA / Normbase / Schemo HTTP APIs

Aperio local agent backend, CLI, and web UI

Official package name for the BenchCAD benchmark suite (placeholder release; the evaluation engine lives on GitHub)

⚡ B-FAST Context Compression Layer for Large Language Models (LLMs)

RAG evaluation library for Indian languages (Hindi, Marathi, Tamil, Bengali, Telugu, Gujarati, Punjabi)

Login to ChatGPT with email:password, get access token + cookies

Manually switch between multiple Claude Code accounts by swapping local credentials.

Real-time LLM cost tracking and optimization — Rust core with Python API

Standalone Confluence RAG MCP retrieval server backed by SQLite/sqlite-vec.

The simplest way to use LLMs

AI-powered git diff analysis and code review with RAG context

Generated gRPC/protobuf stubs for ecom_agent.v1.AgentService

Inspects AI agent projects for ECZ-ID configuration and public evidence posture.

Magento 2 REST API SDK

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

Proxy Gemini (Vertex AI) completions wrapped in OpenTelemetry trace spans; returns the answer plus the trace/span id.

Autonomous MCP agent for graduate school applications: prof discovery + verified cold emails + SOP drafting + application tracking.

GraphSearch: a GraphQL API server for Retrieval-Augmented Generation (RAG) over your documents

LangChain Tool integration for The Factory — x402 micropayment data API

CLI for OpenAI and Anthropic organization cost reports

Safe LLM prompt templating with validation guards

The Mandate Agent SDK — Trust Engine for the Agent Economy

Lightweight durable agent kernel for product integrations

An MCP which adds terminal capabilities to an agent.

htop for local AI inference — curses-based TUI monitor for Ollama, llama-swap/vLLM and ComfyUI: models, GPU and server

A Django storage field that works everywhere. One import. Any backend. Zero plumbing.

Production-grade RAG for Python: ingest documents, hybrid search, streaming, multi-LLM, guardrails. CLI + Python API.

pytest for RAG systems - evaluate retrieval-augmented generation pipelines

Sign LangGraph tool calls and graph nodes with Vouch Credentials.

Azure OpenAI Target adapter for Waken — routes waken Events to an Azure-hosted OpenAI deployment.

AWS Bedrock Target adapter for Waken — routes waken Events to any Bedrock-hosted model via the Converse API.

Claude Target adapter for Waken — routes waken Events to the Claude Agent SDK.

Cohere Target adapter for Waken — routes waken Events to Cohere's chat API.

Gemini Target adapter for Waken — routes waken Events to Google's google-genai SDK.

Groq Target adapter for Waken — routes waken Events to Groq's fast inference API.

Mistral Target adapter for Waken — routes waken Events to Mistral AI's chat API.

Ollama Target adapter for Waken — routes waken Events to a local/self-hosted Ollama daemon.

OpenAI Target adapter for Waken — routes waken Events to the OpenAI Responses API.

ACAIAgent — a model-agnostic layer for the Claude Agent SDK. Switch models mid-session without losing context. Bring your own models.

Supervise external ACP AGENT runs with auditable, redacted local artifacts

Agent402 for LangChain (the applied layer of Agentic Finance): turn Agent402's catalog of 500+ pay-per-call tools and skill packs (x402 or MPP) into LangChain tools for Python agents via four meta-tools. The pure-CPU tools are free via proof-of-work - no wallet, no API keys.

AI Agent 客制化配置中心 — 统一管理多 Agent 配置，一键启动

Runtime control plane for AI agents: live cost metering and circuit breakers

Transparent wrapper for the OpenAI Python SDK to inject CaesuraO recommendations.

Generate release changelogs from directories of changelog fragments

A LangGraph + Ollama coding agent usable as a library via agent.run(query)

Program the Nexus agent in your installed Cosmon app — drive SolidWorks, Abaqus, COMSOL, Fluent and more.

A tiny CLI for delegating bounded agent tasks across coding-agent runtimes.

Framework-agnostic middleware for approving or denying AI agent tool calls.

Magento 2 REST API client for products, customers, attributes, stores and search, part of Entirius

CrewAI integration for GaaS (Governance as a Service)

Pydantic AI integration for GaaS (Governance as a Service)

Open-source security guardrails for LLM applications — prompt injection, jailbreak, PII, hallucination & toxicity detection (with Turkish/KVKK support).