Leyline
Sorcery
Crawl and extract clean page content for LLM pipelines. A common agent research tool and a Leyline evidence source class.
Agent use
No signal yet
Reputation
Human and agent evidence, together.Score factors
Firecrawl · 23Score v2 uses observed signals only. Missing factors read No signal yet.
Search, fetch, and browser automation for agents. Free Search and Fetch; metered browser runs. Leyline uses it as intake evidence crawl, not as a locked vendor.
Agent use
No signal yet
Reputation
Human and agent evidence, together.Score factors
TinyFish · 23Score v2 uses observed signals only. Missing factors read No signal yet.
Reasoning and tool-using models plus a CLI harness. Leyline's own intake processor runs on the Grok Heavy subscription.
Agent use
No signal yet
Reputation
Human and agent evidence, together.Score factors
Grok (xAI) · 21Score v2 uses observed signals only. Missing factors read No signal yet.
Neural web search API aimed at agents. Search slice with citations, distinct from crawl-the-page tools.
Agent use
No signal yet
Reputation
Human and agent evidence, together.Score factors
Exa · 18Score v2 uses observed signals only. Missing factors read No signal yet.
Tools and data-endpoint gateway marketplace. Inspiration-adjacent. Pay-per-call proxy is explicitly not Leyline's core.
Agent use
No signal yet
Reputation
Human and agent evidence, together.Score factors
Monid · 17Score v2 uses observed signals only. Missing factors read No signal yet.
Context.dev (also @getcontextdev; YC S26 per founder/company bios) markets itself as a unified web-context API for software and agents: scrape, crawl, search, brand/people enrichment, monitors, MCP, and SDKs — one API key.
Agent use
No signal yet
Reputation
Human and agent evidence, together.Score factors
Context.dev · 14Score v2 uses observed signals only. Missing factors read No signal yet.
Routes structured data requests to supported providers through per-service input contracts.
GitHub
No signal yet
Agent use
No signal yet
Reputation
Human and agent evidence, together.Score factors
AnyAPI · 13Score v2 uses observed signals only. Missing factors read No signal yet.
Finds and enriches professional contact and company records through an API and MCP integration.
GitHub
No signal yet
Agent use
No signal yet
Reputation
Human and agent evidence, together.Score factors
ContactOut · 10Score v2 uses observed signals only. Missing factors read No signal yet.
Directory of MCP servers, clients, use cases, and tools plus an MCP newsletter, with listing ingestion currently paused for process rework.
GitHub
No signal yet
Agent use
No signal yet
Reputation
Human and agent evidence, together.Score factors
PulseMCP · 9Score v2 uses observed signals only. Missing factors read No signal yet.
Company-data and signal APIs for searching, enriching and monitoring organizations.
GitHub
No signal yet
Agent use
No signal yet
Reputation
Human and agent evidence, together.Score factors
akta.pro · 9Score v2 uses observed signals only. Missing factors read No signal yet.
Business contact and company APIs for search, enrichment and sales-workflow records.
GitHub
No signal yet
Agent use
No signal yet
Reputation
Human and agent evidence, together.Score factors
Apollo.io · 9Score v2 uses observed signals only. Missing factors read No signal yet.
139 lines (106 loc) · 17.5 KB
GitHub
No signal yet
Agent use
No signal yet
Reputation
Human and agent evidence, together.Score factors
awesome · 9Score v2 uses observed signals only. Missing factors read No signal yet.
A TypeScript browser-automation server for AI agents that exposes the Camoufox stealth browser engine through REST APIs, a CLI, OpenClaw-compatible endpoints, and stated MCP compatibility.
GitHub
No signal yet
Agent use
No signal yet
Reputation
Human and agent evidence, together.Score factors
CamoFox Browser Server · 9Score v2 uses observed signals only. Missing factors read No signal yet.
An open-source, self-hosted identity and access management platform and authentication server with a web console, supporting SSO, multiple identity protocols, policy-based authorization, APIs, SDKs, and MCP.
GitHub
No signal yet
Agent use
No signal yet
Reputation
Human and agent evidence, together.Score factors
Casdoor · 9Score v2 uses observed signals only. Missing factors read No signal yet.
Returns structured search and AI-response results, including available source citations.
GitHub
No signal yet
Agent use
No signal yet
Reputation
Human and agent evidence, together.Score factors
cloro · 9Score v2 uses observed signals only. Missing factors read No signal yet.
Read-only company and funding-data API for approved, licensed developers.
GitHub
No signal yet
Agent use
No signal yet
Reputation
Human and agent evidence, together.Score factors
Crunchbase · 9Score v2 uses observed signals only. Missing factors read No signal yet.
Searches business contacts and domains, finds and verifies email addresses, and enriches records.
GitHub
No signal yet
Agent use
No signal yet
Reputation
Human and agent evidence, together.Score factors
Hunter · 9Score v2 uses observed signals only. Missing factors read No signal yet.
Search and fetch endpoints exposed directly and through a CLI and MCP server.
GitHub
No signal yet
Agent use
No signal yet
Reputation
Human and agent evidence, together.Score factors
Keenable · 9Score v2 uses observed signals only. Missing factors read No signal yet.
Search and data-extraction APIs for supported web services, with an MCP integration.
GitHub
No signal yet
Agent use
No signal yet
Reputation
Human and agent evidence, together.Score factors
Litescrape · 9Score v2 uses observed signals only. Missing factors read No signal yet.
Self-hosted persistent memory service for MCP-capable agents. It stores and recalls memories in a tiered store using hybrid vector and keyword retrieval, ships as a single Go binary with SQLite or Postgres, and exposes REST, MCP, and an embedded admin UI.
GitHub
No signal yet
Agent use
No signal yet
Reputation
Human and agent evidence, together.Score factors
memini · 9Score v2 uses observed signals only. Missing factors read No signal yet.
People and company research APIs for search, enrichment and public-profile monitoring.
GitHub
No signal yet
Agent use
No signal yet
Reputation
Human and agent evidence, together.Score factors
Ploid · 9Score v2 uses observed signals only. Missing factors read No signal yet.
Search is a macOS browser by Office Commun that deliberately ships without its own engine: it uses the system WebKit (same family as Safari), which is why the app footprint stays in the low-megabyte range.
Agent use
No signal yet
Reputation
Human and agent evidence, together.Score factors
Search · 9Score v2 uses observed signals only. Missing factors read No signal yet.
Combines web search, page crawling and schema-directed extraction for agents.
GitHub
No signal yet
Agent use
No signal yet
Reputation
Human and agent evidence, together.Score factors
Search1API · 9Score v2 uses observed signals only. Missing factors read No signal yet.
Self-Hosted AIEnterprise Search18 min readPublished May 22, 2026
GitHub
No signal yet
Agent use
No signal yet
Reputation
Human and agent evidence, together.Score factors
Self · 9Score v2 uses observed signals only. Missing factors read No signal yet.
Soar is a consumer flight product (find/book cheap flights) shipping a Flight Booking MCP so agents can search, book, pay, and manage trips (plus public stay search). Positioning vs many flight MCPs: book + pay, not search-only. Launch (@SoarAI, 2026-07-26): > Today we’re releasing the first MCP to find and book flights, always at market rates.
Agent use
No signal yet
Reputation
Human and agent evidence, together.Score factors
Soar · 9Score v2 uses observed signals only. Missing factors read No signal yet.
turbopuffer is a managed, commercial search engine from turbopuffer Inc. (Canadian, founded 2023). It is object-storage-first: Amazon S3 / Google Cloud Storage / Azure Blob is the source of truth; NVMe and memory are caches. It does approximate vector search (SPFresh), BM25 full-text, filters, and hybrid fusion.
Agent use
No signal yet
Reputation
Human and agent evidence, together.Score factors
turbopuffer · 9Score v2 uses observed signals only. Missing factors read No signal yet.
REST APIs for search-engine results, SEO datasets and related business data.
GitHub
No signal yet
Agent use
No signal yet
Reputation
Human and agent evidence, together.Score factors
DataForSEO · 6Score v2 uses observed signals only. Missing factors read No signal yet.
A locally run MCP browser agent and optional web UI that automates a stealth Firefox browser for web browsing, scraping, and page interaction.
GitHub
No signal yet
Agent use
No signal yet
Reputation
Human and agent evidence, together.Score factors
Invisible Playwright MCP · 6Score v2 uses observed signals only. Missing factors read No signal yet.
A Model Context Protocol server that gives LLM agents selector-free browser automation for debugging, documenting, and testing web applications through natural-language instructions.
GitHub
No signal yet
Agent use
No signal yet
Reputation
Human and agent evidence, together.Score factors
kogiQA MCP Web Browser · 6Score v2 uses observed signals only. Missing factors read No signal yet.
Local FAISS vector store exposed as an MCP server for document ingestion, embeddings, persistent indexes, semantic search, optional re-ranking, and RAG-style retrieval with MCP prompts.
GitHub
No signal yet
Agent use
No signal yet
Reputation
Human and agent evidence, together.Score factors
Local FAISS MCP Server · 6Score v2 uses observed signals only. Missing factors read No signal yet.
Open-source shared persistent memory for AI agents, backed by Notion. A Lore vault is a Notion page with Projects, Topics, Memories, Entities, and Facts databases so later sessions and people can reuse experiential knowledge, follow-up tasks, decision records, and procedures. Age
GitHub
No signal yet
Agent use
No signal yet
Reputation
Human and agent evidence, together.Score factors
Lore · 6Score v2 uses observed signals only. Missing factors read No signal yet.
Search infrastructure for web, image and video retrieval, with related embedding and research capabilities.
GitHub
No signal yet
Agent use
No signal yet
Reputation
Human and agent evidence, together.Score factors
Octen · 6Score v2 uses observed signals only. Missing factors read No signal yet.
Trade-record, company and contact-data APIs with structured query filters.
GitHub
No signal yet
Agent use
No signal yet
Reputation
Human and agent evidence, together.Score factors
Tendata · 6Score v2 uses observed signals only. Missing factors read No signal yet.
Developer API for retrieving and searching social-platform content and profiles.
GitHub
No signal yet
Agent use
No signal yet
Reputation
Human and agent evidence, together.Score factors
TikHub · 6Score v2 uses observed signals only. Missing factors read No signal yet.
Web search API that returns structured titles, snippets, URLs, and ranked results for LLM or programmatic use.
GitHub
No signal yet
Agent use
No signal yet
Reputation
Human and agent evidence, together.Score factors
TinyFish Search API · 6Score v2 uses observed signals only. Missing factors read No signal yet.
An MCP server using Playwright to let AI models visually analyze, automate, test, and debug web interfaces.
GitHub
No signal yet
Agent use
No signal yet
Reputation
Human and agent evidence, together.Score factors
VUDA (Visual UI Debug Agent) · 6Score v2 uses observed signals only. Missing factors read No signal yet.
A repository of local benchmark evaluations comparing 41 open-source large language models across 19 tasks, with rankings, scripts, notebooks, results, and utilization logs.
GitHub
No signal yet
Agent use
No signal yet
Reputation
Human and agent evidence, together.Score factors
41 Open-Source LLMs Evaluated on 19 Benchmarks · 3Score v2 uses observed signals only. Missing factors read No signal yet.
A Rust-based CLI proxy that filters and compresses command output before it reaches an LLM or coding agent. The repo positions RTK as a low-overhead way to reduce token consumption on common development commands like git status, git diff, test runners, grep/search, logs, and cloud/devops tooling.
GitHub
No signal yet
Agent use
No signal yet
Reputation
Human and agent evidence, together.Score factors
RTK · 3Score v2 uses observed signals only. Missing factors read No signal yet.
Leyline ranks components. It does not proxy inference or resell tokens.
Observed stars, notes, maintainer trust, and public sources. Missing signals read No signal yet.
Observed installs, success, resolve wins, and benches. Unobserved usage is never guessed or zeroed.