Data agents

Coinbase AgentKit action provider for NodeFlare — read on-chain data across 23 EVM chains (incl. young chains like Robinhood, Plasma, Ink) through one provider, addressed by chain name. No per-chain RPC setup.

Tabstack tools for LangChain.js. Schema-enforced web extraction and research, backed by the official Tabstack SDK.

TradeInsight's finance & trading CLI agent for quants and traders — research the market, backtest strategies, and optimise portfolios in plain language.

Pi extension that syncs models from an OpenAI-compatible API and enriches them with pricing and capability metadata.

Autonomous Mathematical Research Agent for the Riemann Hypothesis. Built on the Artificial Junky Neuron (AJN) framework, extended from quantum-spherifier by Justo Tapiador Garcia (UA). Generates LaTeX/PDF mathematical documents (hypotheses, proofs, theore

MCP server for Run402 — full-stack backend infrastructure for AI agents: Postgres, auth, storage, serverless functions and atomic deploys. Paid with x402/MPP. Includes $0.03 image generation.

OmniBioFex X - The Autonomous Research Operating System

AI-powered local-first commerce engine — orders, inventory, payments, policies, and integrations

Install one middleware. Monetize unused 402 responses with recommendations, discovery, and machine commerce analytics. MCP server: 7 tools for agent demand analytics, paid per call in USDC on Base; free for publishers on their own traffic.

EdgeBase core SDK — platform-agnostic client for auth, database, storage, and functions

React component library for AI-powered assistants in Sisense Compose SDK, providing chat interfaces and tools for analytics, chart building, and dashboard creation.

Atomic, GitHub-native mutex for multi-agent work. The lock IS a git ref — no server, no database. First writer wins.

Canonical Memorix metadata contracts, effective multi-agent resolution, and metadata-only abstract unions (Phase 3).

Advanced memory management system for AI agents with semantic retrieval, hierarchical structures, and multi-agent support

Production MCP server for multi-agent AI research with OpenRouter

Multi-agent skill for safely reading Clarion TopSpeed TPS files with TpsReader.

Multi-agent MCP platform for data centers and critical power.

High-Performance Enterprise AI Project Management MCP Server with advanced optimization and multi-agent coordination

Tabstack tools for the Mastra agent framework. Schema-enforced web extraction and research, backed by the official Tabstack SDK.

Tabstack tools for Vercel's eve agent framework. Schema-enforced web extraction and research, backed by the official Tabstack SDK.

Fan-out search across agentic search providers, merged into deduplicated sources with provenance and cost telemetry

MCP server that lets Claude, Cursor, LangChain and CrewAI call 35 live x402 pay-per-call tools on Base (USDC) with no API key. Agents auto-pay per call via the x402 v2 protocol using their own funded wallet: cited SEC EDGAR company data, RDAP domain-trust

LangChain and LangGraph integration for the Outsail Context Intelligence Platform

Reproducible synthetic test data for CSV and database workflows

Give an agent the channels it needs, and only those. Install per channel, one output shape, with caching and a token budget.

Never worry about your AI agent breaking production again. Kill the process mid-flight — the wire transfer is still safely refunded, your database stays clean, and your users never lose trust. agent-saga is the 1-line bulletproof safety OS that turns unpredictable LLMs into crash-proof, enterprise-grade autonomous engines.

Read your own logged-in Facebook — timelines, feed, comments, search, groups — into clean JSON, over the same GraphQL endpoint your browser uses.

Read-only scraping of logged-in X/Twitter data via a harvest-then-replay hybrid: a stealth-browser login harvests the session once, then reads are replayed over httpx. No client-transaction-id replay.

In-memory observability database for LLM agents: logs tool calls, messages, thinking, responses, tokens, and carried-in context.

AKShare MCP Server — 46 financial data tools for LLMs

Profiler and optimization layer for AI agent execution graphs

MCP server for AgentRank / AgentIndex — search real, verifiable businesses for AI agents.

Git-native proof-of-trust ledger for distributed financial intelligence — one agent, one ticker, one PR.

Validate downloaded partner CSV/Parquet feeds and monitor rolling receipt deadlines

Store time series data as HDF5 files and access them through an API.

Multi-agent stock & crypto screening with leakage-aware (point-in-time) LLM evaluation and an honest, mechanical backtest.

Agent: text / field layout -> dashboard in selected BI on top of DWH DM layer

aws_sdk_bedrock_data_automation client

Full-lazy single-model CRC-LNM research-assistance MCP for ModelScope STDIO

Containerized CRC-LNM research-assistance MCP for Nexent

Xberg document extraction tools for CrewAI agents — text, metadata, and batch extraction across 107 file formats

Python SDK for Cykani stealth browser automation and AI agents

Agentic Data Quality Pipeline: profiles CSVs, proposes DQ rules, writes+validates SQL to check them, and reports confirmed violations.

3D modelling tools for Datasette Agent - create and edit 3D models from chat

Lightweight database query capture agent for DBPulse — real-time monitoring for PostgreSQL, MySQL, and MongoDB

Deep web search agent library built on LangChain deepagents: orchestrator + specialized subagents + iterative rubric-graded refinement.

Domain-specific RAG embedding model for Data Science & ML documentation retrieval

Smart storage engine with data-type routing, multi-tenancy, and schema enforcement

FableForge Agent — a fork of Hermes Agent (NousResearch). A self-improving AI agent that creates skills from experience, improves them during use, and runs anywhere

Epistemic foraging for AI agents and researchers: source discovery, evidence pinning, uncertainty-aware briefs.

Agent-native CLI for Google Analytics 4

Document knowledge graphs — extract structured data from documents (Confluence, PDFs, CSV, JSON, Excel) into Neptune

Universal web collection engine — extract, monitor, and search any website through Cloudflare

Haystack 2.x component that ingests Salesforce Nonprofit Success Pack (NPSP) donor data as Documents for RAG.

Nimble Agent API V2 plugin for Hermes — durable, cited deep-research runs you can start now and resume from any session

Embedded, single-file, in-process vector database.

Give your OpenAI Agents SDK agent a June memory — wrap any Session to mirror conversations into a searchable, cited June knowledge canvas, add a memory-search tool, and backfill existing session databases.

A JupyterLab extension for interactive geospatial data exploration via STAC catalogs and MCP-powered queries.

A zero-config MCP server that turns any folder of documents into a queryable multi-agent knowledge base

ParseRail tools for CrewAI — document parsing, chargebacks, contracts, dunning, lead screening, and cited research as ready-made BaseTools.

An integration package connecting CrustAPI (Google search and public LinkedIn data) and LangChain

LangChain tools for the DexPaprika API: keyless DEX market data across every supported blockchain

LangChain document loader and tool that read the web through ProxyHat residential proxies — rotation, geo-targeting, sticky sessions.

Tabstack tools for LangChain. Schema-enforced web extraction and research, backed by the official Tabstack SDK.

Official LangChain integration for the WellMarked API — load any URL as clean Markdown.

LangChain document loader for Xberg — extract 88+ file formats into Documents with async, batching, chunking, and rich metadata

DM Database checkpoint and Store persistence for LangGraph.

Haystack 2.x integration for the Live Tennis API: live scores, matches and players as Documents

LlamaIndex data loaders for Feishu/Lark wiki, docs, and drive

Official LlamaIndex reader for the WellMarked API — load any URL as clean Markdown.

LlamaIndex tool spec for chDB, the in-process ClickHouse engine: analytical SQL over local files, object storage, and remote databases with engine-level read-only safety.

LlamaIndex web reader that loads URLs through ProxyHat residential proxies — rotation, geo-targeting, sticky sessions.

Model names, pricing, and free-tier metadata for OpenAI, Anthropic, and Google Gemini.

Perplexity's Agent API as a model for Simon Willison's llm CLI.

Deterministic Go and Python sketches for high-cardinality LLM data.

LLM Runner Control is a CLI tool to interact with local and remote LLM, define multiple scenario variations (model × prompt × options), run it over a dataset and capture structured results for comparison or to build knowledge through meta analysis.

RAG Knowledge MCP Server — FastMCP + LanceDB + Hybrid Search

A local citation-aware research and teaching assistant for technical PDFs

Open-source CLI framework for evaluating RAG systems and AI Agents

LangChain and LangGraph integration for the Outsail Context Intelligence Platform

Shared runtime and agent skills for Frowang paper research workflows.

Zero-dependency MCP server for Perplexity's Agent API.

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

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

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

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

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

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

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

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

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

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.

Async storage router across Redis, Upstash, PostgreSQL, and future backends

A simple text-based storage system where you can create tables, store data, and more! Encryption is included for data files.

Ray-native context/memory sharing for parallel research agents, with an agent-native CLI and MCP server (Milestone 1 spike)

Mask PII in LLM tool-call outputs before they reach the model, with role-based access control. Zero dependencies.

An integration of Upstash Vector with Haystack.

AgentKit action provider for VeraData — LATAM sanctions/KYB screening for autonomous AI agents, paid via x402 on Base

Compile CSV/XLSX data and DashboardSpec into validated offline HTML dashboards.