Python agents

LangChain tools for Tanod: address risk checks, smart-contract scans, MCP/skill package scans, web/DNS/chain reads for AI agents. Pay per call with x402 (USDC on Base); free daily tier, no signup.

LangChain tools for Tanvo: let agents generate images, video and songs on Nano Banana, Seedream, Kling, Veo, Seedance and Suno, and run 80 ready-made photo apps. The house image engine works without an API key.

An integration package connecting TopxAI and LangChain

LangChain integration for TranscriptYT: YouTube transcript document loader and agent tools.

Shared-budget extractive context trimming for LangChain.

Model-agnostic LangChain middleware that keeps only the last N conversational turns, without splitting tool_call/tool_result pairs.

A LangChain Tool that solves Cloudflare Turnstile via the Peak API, for agents that drive a browser and hit a challenge.

LangChain tools for TwittrAPI: read public Twitter/X tweets, profiles, followers and search results. Pay as you go from $0.065 per 1,000 calls.

LangChain tools to publish, schedule and analyze social media posts with Upload-Post (TikTok, Instagram, YouTube, LinkedIn, X, Facebook and more).

LangChain tools, toolkit and document loader for URLpipe: read any web page as Markdown, or get its metadata, data in your own fields, its technologies, console errors or a Lighthouse audit, rendered in real Chrome.

LangChain tool for Veida AI image generation, usable with no API key

LangChain and LangGraph callback for AI usage costs, customer attribution and Veqen budgets.

LangChain integration for Vera by Waggle: read pages, search the web, results pages, keyword ideas, AI answers, GEO radar, company footprints and a document loader.

LangChain tools: check an EVM address on Base before sending it funds (safe/caution/danger, or a $0.01 lite screen that never says safe). Pays per call via x402 in USDC from your agent's wallet, within caps you set.

LangChain tools for Wayza: give your agent an address, so it can ask people and other AIs and answer their links.

LangChain tools for WebExtract: extract_url (Markdown + product/price/tables JSON) and page_markdown. Pay per call with x402, prepaid key, or free tier.

LangChain integration for Wity, the typed-decision API

LangGraph checkpointer and long-term memory store backed by HotKV, a RESP2/RESP3-compatible in-memory data store with built-in AI and LLM-serving features.

Secure external human-in-the-loop approvals (Telegram, N options, one-time account connection) for LangGraph interrupts

Graph of Agentic Thoughts: Bridging Agentic Reasoning and Explainability through Graphs

A typed probabilistic decision node for LangGraph, powered by TypeSafe's Jev.

LangGraph long-term memory on MinnsDB: a store that keeps every version, and graph memory that knows which facts are current.

Qdrant-backed long-term memory store for LangGraph.

Composable RAG framework and evaluation harness: change one of eight pipeline stages, hold the rest fixed, and benchmark the change against a baseline.

LiteLLM-backed OpenAI Agents handler for LaunchDarkly AI SDK

LiteLLM messages handler for LaunchDarkly AI SDK

OpenCode agent handler for LaunchDarkly AI SDK

Vercel AI SDK agent handler for LaunchDarkly AI SDK

Coding-agent analysis plugin for `ldw init --agent` in the Local DevOps Workbench.

LeakHunterX Security Scanning Agent

Deterministic coordinate pre-routing and epistemic abstention for legal RAG

Sentence-level claim and NLI verification with KV-cache rollback during generation, for legal RAG

Fence-aware Consul server reconciler for Docker Swarm

Docker Swarm leader election with fencing, supervision, and an observation API

GPT Image by Ace Data Cloud: generation and same-task retrieval for Langflow

Python SDK for Liege agent operators

A lightweight, modular agentic AI framework built from scratch — no LangChain, no CrewAI, no magic.

A Lightweight Defense Architecture Against Indirect Prompt Injection in Tool-Calling AI Agents and MCP Workflows

Hybrid System-One Local Decision Engine (JevCompat 32/32 MUST, AnyJev L0 Prefill, StartLux Read-or-Think Cascade, OpenJev-RLCD Trainer)

A coding-agent harness: LLM decides, the harness dispatches tools, guards and logs

Tiered team budget enforcement and graceful downgrade for a LiteLLM gateway

Self-audit CLI: scan a codebase and local Python environments for exposure to the compromised LiteLLM v1.107.0 release (PyPI, Docker Hub, GHCR) and generate an evidence report, based solely on LiteLLM's official incident announcement.

Library to easily interface with LLM API providers

Flags LiteLLM proxy settings that cost money or break at scale, like background health checks multiplied across every process

Claude Code for the livery workshop: CLAUDE.md, the delivered guidance, .claude/ and the hook verbs the agent's tooling runs.

Each package's coverage floor in the livery workshop, judged on the union of what every CI leg measured, the record that carries it across runs, and the site's coverage pages.

Living Agents Protocol (LAP) Python reference implementation and MCP server middleware: LIP-1 Passport, LIP-3 Scope Algebra, LIP-4 Micro-Core verification and receipts.

ExtractBench: a benchmark and evaluation harness for schema-guided document extraction on real-world enterprise documents

Native Ace Data Cloud LLM integration for LlamaIndex

LlamaIndex LLM for BlockRun: one OpenAI-compatible gateway, paid per call in USDC over x402 on Base or Solana. No API key.

LlamaIndex LLM integration for Runcrate: 200+ open models behind one OpenAI-compatible API

Geniffy for LlamaIndex: a memory of each of your users, for any LlamaIndex agent. A memory block and tools.

LlamaIndex memory block and retriever for Gnarl agent memory

past dev memory block for LlamaIndex agents: recall and ingest long-term memory with the past dev Memory API

Shared-budget extractive context trimming for LlamaIndex text nodes.

LlamaIndex reader for Anakin: load web pages, crawls, search results and site maps as Documents

LlamaIndex reader for the AnyToMarkdown API: PDF, Word, Excel, PowerPoint and web pages to Markdown.

llama-index readers contextfetch integration

LlamaIndex reader for DataSinking — full-text financial reports as documents

Decodo web scraping API reader for LlamaIndex — load web pages and search results as Documents.

LlamaIndex reader for docling.rs: PDF with layout, tables and OCR, DOCX, PPTX, XLSX, HTML and 40-odd formats into LlamaIndex Documents as Markdown or docling JSON. docling in Rust, no PyTorch.

YouTube transcript reader for LlamaIndex: load YouTube video transcripts (optionally with timestamps) as Documents for RAG, via the GetYouTubeTranscript API. Works from cloud servers without proxies.

LlamaIndex reader for MeshArc: web pages, crawls, sitemaps and change records as Documents.

LlamaIndex reader for PDFluent: PDF blocks, tables or markdown pages with page, box, kind and confidence, locally, fast or balanced quality.

llama-index readers printfriendly integration: load any web page as clean, ad-free Markdown

LlamaIndex readers for Scrape.ly: run Actors or read datasets and get Documents back.

LlamaIndex reader for superPDF AI: local PDFs as Markdown with tables, charts as data and OCR.

LlamaIndex reader for URLpipe: load web pages as clean Markdown, rendered HTML or a summary, rendered in real Chrome.

llama-index tools agentsearch integration: free live web search, plus pay-per-call extract and JS render

LlamaIndex tools for Anakin: web scraping, search, deep research, Wire site actions, monitors and browser tasks

LlamaIndex tool spec for BotsRated: free pre-payment preflight of x402 sellers, opt-in budgeted paid checks.

llama-index tools carejobs integration: open US healthcare jobs, pay and employers from CareJobs.Now

llama-index tools clawfetch integration — pay-per-call web intelligence for AI agents (x402, USDC on Base)

llama-index tools contextfetch integration

Decodo web scraping API tool spec for LlamaIndex agents.

LlamaIndex tool spec for the DeepInquiry verified-facts API: cited, tier-scored, signed facts.

LlamaIndex tools and a reader for EconDash time series across ten categories: macroeconomics, financial markets, labor, demographics, real estate, energy, transport, healthcare, education and technology.

Google and YouTube search tools and citation-aware readers for LlamaIndex

LlamaIndex tools for Geekflare: web search, Google SERP, scraping, screenshots, PDFs, brand data, and website diagnostics.

LlamaIndex tool spec for Layrcake: find leads, enrich and verify emails, check and research companies, and draft campaigns that a person approves before anything sends.

LlamaIndex tool spec for Machine Library: citable search over papers, books, patents, standards and Wikipedia.

past dev tools for LlamaIndex agents: recall and ingest with the past dev Memory API

Email inboxes for LlamaIndex agents: send, read, search, wait for verification codes and reply, with Pidgeon.

Give a LlamaIndex agent lead lists, company lists and grants from the live web. Every row comes with its source, priced per match in code.

Steward MCP tools for LlamaIndex — 25 tools for x402 agent commerce (trust verification, spend controls, merchant directory, paid API endpoints)

LlamaIndex tool spec for Tanod: web search, page/PDF/document to Markdown, screenshots, OCR, DNS and email checks, phishing URL check, address risk, contract and package scans for AI agents. Free daily tier, then x402 USDC.

LlamaIndex tools for TwittrAPI: read public Twitter/X tweets, profiles, followers and search results. Pay as you go from $0.065 per 1,000 calls.

LlamaIndex vector store for Cairn, the hybrid search database where a deletion is final

LlamaIndex integration for Wity, the typed-decision API

Llama Stack out-of-tree eval provider (remote::csoai): verify CSOAI signed evidence batches offline and return each event's state, never a score.

Unified Efficient Fine-Tuning of 100+ LLMs

Evaluate and observe LLM-powered applications with deterministic metrics and LLM-as-Judge.

Record and replay LLM agent SDK and tool calls for offline pytest.

AI SDK for Python adapter for llm-catalog: build native `ai` models from a catalog config, routed through your gateway.

Use your ChatGPT plan via Sign in with ChatGPT OAuth

DeepSeek web search and fetch tools for LLM

A local CLI tool for evaluating LLM prompt outputs against test suites

CI/CD quality gate framework for LLM and RAG applications: metric, schema, and security testing with a pytest-native workflow.

Advanced LLM Fine-Tuner — SFT, DPO, ORPO, KTO, GRPO, reward modelling and evaluation

LLM plugin for models hosted by FlexAI