fast-graphrag
AI developer platformsRAG that intelligently adapts to your use case, data, and queries.
3,631 results · Page 69 of 101
RAG that intelligently adapts to your use case, data, and queries.
FastAgent is a runtime and adapter layer that publishes a local agent directory as an online service. It does not introduce a new agent-authoring DSL, but instead reuses your existing directory structure: Markdown instructions, reusable Skills, and TypeScript tools still exist as files. FastAgent is responsible for connecting these definitions to Next/Astro applications, Telegram, Slack, Feishu/Lark, HTTP/SSE interfaces, or custom channels, providing streaming replies, group awareness, and webhook validation. It has built-in multi-model support based on the open-source pi harness (OpenAI, Anthropic, Google, etc.), tools are validated through defineTool and Zod, and Agent Skills are loaded on demand. It emphasizes a small-core philosophy: invoke decouples channels, agents, harness, and infrastructure, and does not take over your authentication, database, routing, and deployment. You can use fastagent deploy to generate containers and configurations for Docker, Fly, Railway, and AWS Bedrock AgentCore, or embed it directly into an existing application with a single route. The project is MIT licensed and is currently in a pre-1.0 version.
FastAPI-MCP is a development library that exposes FastAPI endpoints as Model Context Protocol (MCP) tools, with built-in authentication based on FastAPI dependencies. It is implemented in a FastAPI-native way, rather than being a simple OpenAPI-to-MCP converter. With minimal configuration, it can point to a FastAPI application and run, while preserving the schemas of request models and response models as well as the Swagger documentation for all endpoints. The library supports flexible deployment: the MCP server can be mounted on the same application or deployed separately, and it uses ASGI transport to communicate efficiently directly through FastAPI's ASGI interface. Installation is recommended with uv, and pip can also be used.
#### Overview
A powerful tool for creating high-quality training datasets for Large Language Models
NVIDIA Framework for LLM Inference(Transitioned to TensorRT-LLM)
High-level framework for building MCP servers in TypeScript.
🎖️ 📇 🏠 ☁️ 🍎 🪟 🐧 - Destiny charting: BaZi, Zi Wei Dou Shu and Western astrology natal charts, with true solar time correction and Chinese, English, Japanese and Korean input.
Parse, edit and generate Final Cut Pro FCPXML timelines: health checks, flash frame detection, chapter markers, rough cuts and NLE export.
FDA and NHTSA regulatory risk data: device compliance risk, 510(k) evidence, predicate chains, postmarket signals, reimbursement pathways and vehicle safety.
Freedom-of-information requests in Germany via FragDenStaat: find the responsible authority, check the law and deadline, track requests and draft new ones.
curated custom GPTs list for daily tasks
An AI authentication model focused on optical technology, used to identify counterfeits.
Query FEC campaign finance data via the OpenFEC API: search candidates, track donations, analyze spending and monitor Super PAC activity.
Search the Feedbagel RSS catalog, follow feeds and route new entries to webhooks.
Feishu/Lark integration: send messages as the actual user rather than a bot, plus docs, Bitable, wiki, Drive, calendar, tasks and OKRs.
Deterministic security scan of public git repositories: vulnerable dependencies via OSV, hard-coded secrets and risky config lint, as file:line findings.
a meta-benchmark that evaluates how well factuality evaluators assess the outputs of large language models (LLMs).
🎖️ 📇 ☁️ - Query FEODE offshore oilfield services: well plug and abandonment, subsea wellheads, continuous circulation drilling and a drill-string spec reference.
Math engine combining SymPy, NumPy and Matplotlib for symbolic algebra, numerical computing and data visualization.
URL fetcher and HTML-to-Markdown converter with layered prompt injection defense: hidden-element sanitization, risk scanning and content boundary wrapping.
Fetch web page content using a Playwright headless browser, supporting JavaScript rendering, content extraction and Markdown or HTML output.
All-in-One SEO & Web Intelligence Toolkit API FetchSERP
Connect to FHIR servers, for example to query patient history in natural language.
Perform queries and entity operations in your Fibery workspace.
AI Observability and Security platform for monitoring and protecting LLM and ML models.
Local-first memory with verbatim recall, querying, health checks and context-sensitive orientation, using LLM-free retrieval by default.
Read-only filesystem exploration, search and analysis with symlink protection.
Filming locations of films, series, games and anime: where a title was shot, what was shot at a place and what is nearby, from open Wikidata-based data.
Compare approximate filter data structures: Bloom, Counting Bloom, Cuckoo and SuRF.
Generate localized debt-collection demand letters as PDFs, with matching envelopes, for many jurisdictions and languages.
Market data and analysis: stock quotes, technical indicators, CoinGecko crypto prices, risk metrics, options chains and portfolio analysis.
🎖️ 🐍 ☁️ 🏠 - Alternative financial data from FinBrain.
Domain availability checking and WHOIS lookup tools.
Real-time stock data, company fundamentals, FRED economic indicators, SEC filings and crypto prices, paid per call via x402 on Base.
Access financial data from multiple providers, such as Tushare.