Python agents

Interfaze Langchain SDK

Local-first evidence-based career decision support for Japan job seekers: confirmed facts, conflicts, unknowns, verification, and user-controlled next actions.

Turn any agent into a self-learning system that learns from user feedback - safely, with two lines of code.

Local-first self-healing Ubuntu terminal agent. Type in English, get shell commands with risk checks and smart retries.

Retrieval-augmented Q&A over the CSUF Nautilus JupyterHub user guide, run in-process inside a student's own JupyterHub instance.

JupyterLab sidebar chatbot grounded in the CSUF JupyterHub user guide.

A native Python port of kiln — build and orchestrate AI agents: unified providers (OpenAI/Groq/Ollama), a tool-calling loop, self-correcting structured output, MCP support, and a DAG orchestrator.

Native LangChain integration for the Apertis AI API

LangChain tools, loaders, retrievers, and inbound email events for CarlyEmail.

LangChain tools for ERC20 primitives: balances, allowances, transfers, approvals, and native wrap/unwrap, as execution plans an EOA can sign or a smart-contract wallet can batch.

LangChain document loader that turns PDFs and images into Markdown documents with the HexRead API.

LangChain tools for generating privacy-safe synthetic financial data for Latin American fintech applications.

LangChain tools that return finished files: PDF, docx, charts, subtitles, invoices, screenshots — one hosted endpoint, free quota, no API key to start.

OpenSandbox sandbox backend for LangChain deep agents

A LangChain document loader and blob parser for PDF files, built on the pdf-inspector library.

TollWarden payment security for LangChain/LangGraph agents: scan x402 payments before settling, auto-tag provenance for prompt-injection detection, guard payment tools so blocked payments can never execute.

YantrikDB integration for LangChain — cognitive memory as a VectorStore and ChatMessageHistory. Stored memories decay, consolidate, and get contradiction-checked.

LangGraph checkpoint saver backed by Supabase (Postgres via PostgREST).

LangGraph BaseStore implementation backed by Upstash Redis (REST client).

LangGraph nodes/tools to monetize graph steps via U.CASH (HTTP-402). Non-custodial.

LangChain/LangGraph agent handler for LaunchDarkly AI SDK

LangChain messages handler for LaunchDarkly AI SDK

OpenAI agent handler for LaunchDarkly AI SDK

OpenAI messages handler for LaunchDarkly AI SDK

Python client SDK for InfraX RAGservicer — hybrid knowledge-base (vector + graph + keyword) retrieval

LiteLLM proxy logging callback that appends request telemetry to DuckLake tables through an Arrow Flight SQL endpoint

Paritok context compression as a LiteLLM Proxy callback — tool filter + content/history compression + non-destructive recall + edit recovery, transparently on every request through LiteLLM Proxy.

Bill LiteLLM LLM proxy calls via U.CASH pay-per-token. Non-custodial.

Native OpenAI-compatible agent harness for LiteyukiBot v7.

Declarative agent module and tool resolver for LiteyukiBot v7.

Sub-20ms prompt injection and jailbreak protection for LlamaIndex query engines.

llama-index llms TrustedRouter integration

llama-index postprocessor needlepath context selection integration

LlamaIndex reader that turns PDFs and images into Markdown documents with the HexRead API.

llama-index tools olostep integration

LlamaIndex integration for Lumify — load all Lumify sports-intelligence tools (schedules, live scores, odds, betting splits, explainable AI bet confidence) into any LlamaIndex agent via MCP.

A self-healing local-LLM wiki that compounds your documents across working, episodic, semantic, and procedural memory tiers.

Resilient Multi-Provider LLM Fallback Router (DeepSeek, OpenAI, Ollama, Anthropic).

LLM plugin for Microsoft Foundry models, authenticated via Azure CLI

Local collector for LLM token usage emitted through OpenTelemetry

Lightweight provider router foundation.

Practical, FOSS-backed security gates for LLM systems: model-file supply-chain gate, runtime I/O firewall proxy, and model resilience scoring.

Automated vulnerability scanner for applications that integrate Large Language Models, covering the OWASP Top 10 for LLMs.

Zero-shot decision tree induction and embedding using large language models

Unified interface for interacting with multiple LLM providers.

Autonomous Product Foundry — opportunity discovery, prompt orchestration, identity management, application generation, compliance, marketing, launch, and continuous improvement

AI-security auditor — score any AI endpoint against Responsible-AI metrics, plus a 44-control safety register (early/experimental)

Audit trail, authorization, and anomaly detection for AI agents

Serve llms-txt documentation over MCP (MCP Python SDK v2 / 2026-07-28 spec)

Local-first telemetry and tamper-evident receipts for AI-agent runs

Enterprise memory-sharing CLI agent harness for coding, governed data, and productivity work.

Mahmood — a terminal agent, powered by Groq, that operates your machine: shell, files, macOS automation, browser, and HTTP APIs.

MARLA: Multi-Agent Reinforcement Learning Architecture for NASimEmu

Synap memory integration for deepagents — a memory backend, retrieval middleware, and tools

Model-agnostic text agents with associative graph memory, consolidation and dataset export

A terminal-based coding agent tool inspired by Claude Code

Local-first RAG MCP server: hybrid search over your documents, fully local

OpenAI Agents SDK invocation for ml-pipes

OpenAI Agents SDK invocation for ml-pipes

OpenAI Responses API invocation for ml-pipes

Autonomous multi-agent ML research platform

Moesif observability plugin for LiteLLM

Mutiny Adapter #1 — OpenAI Agents SDK TargetAdapter

Type annotations for boto3 AgentRegistry 1.43.106 service generated with mypy-boto3-builder 8.12.0

Type annotations for boto3 AgentRegistryControl 1.43.113 service generated with mypy-boto3-builder 8.12.0

Needlepath context selection for LangChain agents (AgentMiddleware) and LangGraph.

Needlepath context selection as a LiteLLM proxy CustomGuardrail.

News sentiment scores (positive/negative) as a ready-made tool for LangChain, CrewAI, AutoGen, and any tool-calling AI agent. Weekly or daily series, period-over-period growth. Powered by trendsmcp.ai

News article mention volume as a ready-made tool for LangChain, CrewAI, AutoGen, and any tool-calling AI agent. Weekly or daily series, growth percentages. No media database subscription. Powered by trendsmcp.ai

Official Python SDK for the Centralized LLM Platform

npm download trends as a ready-made tool for LangChain, CrewAI, AutoGen, and any tool-calling AI agent. Weekly download series, growth percentages, and live trending packages. Powered by trendsmcp.ai

NDJSON-over-stdio daemon exposing the Nullain Agent SDK to editor and CLI clients

AI agent activity monitor — Python port of github.com/perplexityai/numbat

Local ChatGPT-style system

Pacifica trading MCP server, measured-edge setups, exchange-native brackets, funding carry, and a policy-governed autonomous trading entity

Tools to query and consume Open Knowledge Format (OKF) data catalogs, usable standalone or integrated with AI agent frameworks.

Pre-flight checker for local Ollama models

TTTPS Proof-of-Time reverse proxy for Ollama: cryptographic audit-trail timestamps for local model responses via the public KPP Provenance API

LLM-assisted OpenModelica modeling: a tested agentic generate-compile-simulate-verify loop with structured omc diagnostics, quantitative trajectory verification, and a benchmark task ladder.

Compose agents into a graph over oneharness/onejudge and merge their outputs into one event stream.

轻量级的 OpenAI 大模型 IO 库：chat / completions / embeddings，基于 httpx，langchain 风格 message

Haystack integration for opendataloader_pdf

OpenInference Cohere Instrumentation

OpenInference Ollama Instrumentation

HTTP client and JSON schemas for SrvMan-style agent APIs.

Optimizer Agent

An MCP server that lets AI agents extract text and tables from PDFs (invoices, reports, statements).

Use OpenAI, Gemini, and any OpenAI-compatible model inside the Claude Code CLI.

Unofficial async Python RPC client for Prime Agent

A stateful LLM agent framework on pydantic-ai: session persistence, context-window management, and a lifecycle extension system

Terminal chat assistant for software/coding questions, powered by Gemini with Grok fallback.

Q SDK — Instrument any AI agent with security governance

Agent Kernel, local Runtime Plane, standard plugins, and Host

Python SDK for Qoder Agent

AI assistant for semantic search and chat with codebases

Regression testing and configuration sweeps for RAG pipelines.

MiniLM-based intent classifier with 156 intents, including follow-up, negative sentiment, escalate intents detection for RAG systems. Python 3.9-3.13 supported.

TTTPS Proof-of-Time provenance metric for Ragas: verify that a response carries a genuine audit-trail timestamp from the public KPP Provenance API