Leyline
Sorcery
Open protocol so tools, data, and prompts plug into many harnesses. The connect slice Leyline ranks, not a marketplace.
Agent use
No signal yet
Reputation
Human and agent evidence, together.Score factors
Model Context Protocol · 23Score v2 uses observed signals only. Missing factors read No signal yet.
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.
Repo host whose stars, commits, and issues feed Leyline GitHub health — a Score factor, not the whole reputation story.
Agent use
No signal yet
Reputation
Human and agent evidence, together.Score factors
GitHub · 21Score v2 uses observed signals only. Missing factors read No signal yet.
Browser automation for tests and agents. Use the browser slice without taking the whole test-runner product box.
Agent use
No signal yet
Reputation
Human and agent evidence, together.Score factors
Playwright · 20Score v2 uses observed signals only. Missing factors read No signal yet.
Data framework for retrieval and agents. Memory and index slices, not a whole 'RAG product' box.
Agent use
No signal yet
Reputation
Human and agent evidence, together.Score factors
LlamaIndex · 18Score v2 uses observed signals only. Missing factors read No signal yet.
Workflow automation. Compose and schedule slices that agents can call without owning the whole iPaaS.
Agent use
No signal yet
Reputation
Human and agent evidence, together.Score factors
n8n · 18Score v2 uses observed signals only. Missing factors read No signal yet.
Unified model and inference router. Listed honestly as an inference gateway — inspiration-adjacent, not Leyline's core.
Agent use
No signal yet
Reputation
Human and agent evidence, together.Score factors
OpenRouter · 18Score 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.
Hosted browsers for agents. Browser slice without running Playwright locally.
Agent use
No signal yet
Reputation
Human and agent evidence, together.Score factors
Browserbase · 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.
Infinite canvas SDK. Sorcery uses a tldraw-style diagram as the composition map, with logos for registry slices.
Agent use
No signal yet
Reputation
Human and agent evidence, together.Score factors
tldraw · 15Score v2 uses observed signals only. Missing factors read No signal yet.
Anthropic's terminal coding agent. Harness grid deep-link target for the Leyline scour skill.
Agent use
No signal yet
Reputation
Human and agent evidence, together.Score factors
Claude Code · 15Score v2 uses observed signals only. Missing factors read No signal yet.
OpenAI coding agent / CLI. Another day-one harness on the Leyline install grid.
Agent use
No signal yet
Reputation
Human and agent evidence, together.Score factors
Codex · 15Score v2 uses observed signals only. Missing factors read No signal yet.
Tracing and evals for LLM apps. Observe and evaluate slices that feed Score later.
Agent use
No signal yet
Reputation
Human and agent evidence, together.Score factors
LangSmith · 15Score 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.
Open-source real-time global intelligence / situational-awareness dashboard — AI-synthesized news, multi-layer maps, finance/infra/military/disaster signals, plus first-class agent surfaces (MCP, REST, CLI, SDKs). README one-liner: AI-powered news aggregation, geopolitical monitoring, and infrastructure tracking in a unified situational awareness interface.
Agent use
No signal yet
Reputation
Human and agent evidence, together.Score factors
World Monitor · 14Score v2 uses observed signals only. Missing factors read No signal yet.
Gives agents structured desktop accessibility reads and actions through a CLI, C library and MCP server.
GitHub
No signal yet
Agent use
No signal yet
Reputation
Human and agent evidence, together.Score factors
agent-desktop · 13Score 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.
## Here are 48 public repositories matching this topic...
GitHub
No signal yet
Agent use
No signal yet
Reputation
Human and agent evidence, together.Score factors
Build software better, together · 13Score v2 uses observed signals only. Missing factors read No signal yet.
Surfaces (same registry/balance claim): 1. Skill — one-liner set up https://monid.ai/SKILL.md (version 0.1.7) 2. Remote MCP — https://mcp.monid.ai/v1 3. CLI — npm i -g @monid-ai/cli@latest then monid setup / monid discover / run flows 4. HTTP API — https://api.monid.ai/v1/ (Bearer key) 5.
Agent use
No signal yet
Reputation
Human and agent evidence, together.Score factors
Monid · 13Score v2 uses observed signals only. Missing factors read No signal yet.
Gateway layer that routes model calls, discovers MCP tools, and applies identity, policy, and spend controls before invocations.
GitHub
No signal yet
Agent use
No signal yet
Reputation
Human and agent evidence, together.Score factors
MCP / AI Gateway · 12Score v2 uses observed signals only. Missing factors read No signal yet.
Human-in-the-loop training data, RL environments, and evaluation for AI agents and LLMs.
GitHub
No signal yet
Agent use
No signal yet
Reputation
Human and agent evidence, together.Score factors
Toloka · 12Score v2 uses observed signals only. Missing factors read No signal yet.
Open-source application platform to build, deploy, operate, and scale apps on infrastructure you own (VPS, dedicated, cloud VM, homelab). Pitch: replace a pile of deployment tools + managed services with one OSS control plane. Interfaces claimed: web dashboard, native desktop app, CLI, REST API, MCP for AI agents.
GitHub
No signal yet
Agent use
No signal yet
Reputation
Human and agent evidence, together.Score factors
OpenShip · 11Score v2 uses observed signals only. Missing factors read No signal yet.
bb is an MIT-licensed, self-hosted agentic IDE that coordinates installed coding-agent CLIs in persistent, steerable threads. Its first-class control surfaces are a desktop app, web app, CLI, and HTTP API. The project’s central differentiator is that much of its UI/workflow surface is implemented as plugins, so an agent can extend the IDE itself rather than only working inside a fixed product.
Agent use
No signal yet
Reputation
Human and agent evidence, together.Score factors
bb · 10Score v2 uses observed signals only. Missing factors read No signal yet.
Box is a managed sandbox product from Ascii (legal entity Dedale AI, Corp.). It sells persistent Linux VMs for coding agents and agent platforms: SSH, Docker inside the VM, a dedicated IPv4 per machine, snapshot/stop/resume, fork-from-snapshot, optional 60fps desktop stream, and a CLI/API/box prompt path for Claude Code or Codex.
Agent use
No signal yet
Reputation
Human and agent evidence, together.Score factors
Box · 10Score 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.
Ditto is an open-source deterministic website cloner from ion.design. Point it at a public URL and it returns a cloned implementation as componentized Next.js or Vite code (Tailwind styling), with marketing copy citing ~5 minutes end-to-end.
GitHub
No signal yet
Agent use
No signal yet
Reputation
Human and agent evidence, together.Score factors
Ditto · 10Score v2 uses observed signals only. Missing factors read No signal yet.
Developer interfaces for speech generation, transcription, audio and voice-agent workflows.
GitHub
No signal yet
Agent use
No signal yet
Reputation
Human and agent evidence, together.Score factors
ElevenLabs · 10Score v2 uses observed signals only. Missing factors read No signal yet.
README: a CLI for exploring OpenTelemetry traces, metrics, and logs locally. Go custom Collector distribution, DuckDB backend, Svelte UI. Receives OTLP on localhost:4317 (gRPC) and localhost:4318 (HTTP). UI at localhost:8000. In-memory by default; --db persists DuckDB.
Agent use
No signal yet
Reputation
Human and agent evidence, together.Score factors
otel-desktop-viewer · 10Score 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.
Provides model and service access through documented APIs, SDKs and MCP tools.
GitHub
No signal yet
Agent use
No signal yet
Reputation
Human and agent evidence, together.Score factors
BlockRun · 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.
Open-source memory system for agents and teams. It connects company sources such as Slack, GitHub, and Linear so agents can recall shared context through one memory API, an SDK, or an MCP server, with an optional Cognee Cloud for managed scale.
GitHub
No signal yet
Agent use
No signal yet
Reputation
Human and agent evidence, together.Score factors
cognee · 9Score v2 uses observed signals only. Missing factors read No signal yet.
Concentrate is a managed LLM gateway: one API base URL (https://api.concentrate.ai/v1) for hundreds of models across all major providers (OpenAI, Anthropic, Gemini, DeepSeek, etc.). You pick the model and provider; Concentrate runs the request, applies your fallbacks and limits, and surfaces spend/logs.
Agent use
No signal yet
Reputation
Human and agent evidence, together.Score factors
Concentrate.ai · 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.
Fetches rendered web pages as source-linked Markdown and structured page state for agents.
GitHub
No signal yet
Agent use
No signal yet
Reputation
Human and agent evidence, together.Score factors
Expand Fetch · 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.
Extracts web data through scraping agents and programmable workflows.
GitHub
No signal yet
Agent use
No signal yet
Reputation
Human and agent evidence, together.Score factors
MrScraper · 9Score v2 uses observed signals only. Missing factors read No signal yet.
OpenRouter is a unified large language model inference router and model marketplace: one OpenAI-compatible HTTP application programming interface across many underlying inference providers, with automatic fallbacks and cost-aware routing. The marketplace object is models and inference providers (tokens in → tokens out), not installable agent tools ranked by dual human-and-agent reputation.
Agent use
No signal yet
Reputation
Human and agent evidence, together.Score factors
OpenRouter · 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.
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.
Hosted observability for AI/LLM apps. Product line: every model call, tool step, and retrieval in one OpenTelemetry trace, with tokens, cost, latency, and errors. Ingest via TypeScript or Python SDKs, or any OTLP exporter. Cost is computed server-side against 4700+ models.
Agent use
No signal yet
Reputation
Human and agent evidence, together.Score factors
telemetry.dev · 9Score v2 uses observed signals only. Missing factors read No signal yet.
tldraw offline is tldraw’s local, file-based desktop infinite canvas (no accounts / no server required for core use). Documents save as portable .tldraw files (canvas + media + optional embedded document scripts). The 2026-08-03 @tldraw post demos the agent-native angle: you can make your own tools on the canvas — e.g.
Agent use
No signal yet
Reputation
Human and agent evidence, together.Score factors
tldraw offline · 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.
Larasend is an open-source, self-hosted transactional email platform for Laravel teams. It provides a clean HTTP API (POST /api/emails), dashboard, activity log, scoped API keys, delivery events, suppressions, rendered previews, DKIM/DNS guidance, and a Laravel mail transport while sending through your own Amazon SES account.
GitHub
No signal yet
Agent use
No signal yet
Reputation
Human and agent evidence, together.Score factors
Larasend · 7Score v2 uses observed signals only. Missing factors read No signal yet.
Returns typed judgments and probabilities from software state and narrowly defined questions.
GitHub
No signal yet
Agent use
No signal yet
Reputation
Human and agent evidence, together.Score factors
TypeSafe Jev · 7Score v2 uses observed signals only. Missing factors read No signal yet.
Model APIs for text, vision, speech and embeddings, with compatible developer interfaces.
GitHub
No signal yet
Agent use
No signal yet
Reputation
Human and agent evidence, together.Score factors
Alibaba Cloud Model Studio · 6Score v2 uses observed signals only. Missing factors read No signal yet.
Model APIs and SDKs for reasoning, multimodal understanding, and image and video generation or editing.
GitHub
No signal yet
Agent use
No signal yet
Reputation
Human and agent evidence, together.Score factors
BytePlus ModelArk · 6Score 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.
Developer APIs for language and multimodal generation, including speech, images, video and music.
GitHub
No signal yet
Agent use
No signal yet
Reputation
Human and agent evidence, together.Score factors
MiniMax · 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.
Image-generation and editing models available through OpenAI developer APIs.
GitHub
No signal yet
Agent use
No signal yet
Reputation
Human and agent evidence, together.Score factors
OpenAI GPT Image · 6Score v2 uses observed signals only. Missing factors read No signal yet.
Telephony APIs that provision agent phone numbers and support voice calls and SMS.
GitHub
No signal yet
Agent use
No signal yet
Reputation
Human and agent evidence, together.Score factors
Saperly · 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.
A family of real-estate data and integration APIs spanning listings, mortgages, rentals and property information.
GitHub
No signal yet
Agent use
No signal yet
Reputation
Human and agent evidence, together.Score factors
Zillow Data & APIs · 6Score 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.