Component catalogue

156 records

22 of 156 match

Clear

[ Comparison ]

build

Prime Agent leads with Score 9. Cost is unknown. The licence is MIT. Agent and composability metrics are insufficient evidence.

Browse filters
kitintake
agent-desktop

Gives agents structured desktop accessibility reads and actions through a CLI, C library and MCP server.

Function

Observe

watch a system

Observe Browse Observe

Function

Tool-call

invoke an external action

Tool-call Browse Tool-call

Function

Browser

operate a live page

Browser Browse Browser

Interface

cli

Command-line interface

Open spec

Interface

sdk

Language SDK

Open spec

Interface

mcp

Model Context Protocol server

Open spec

Matched agent

GitHub

No signal yet

Agent use

No signal yet

Reputation

Human and agent evidence, together.

Score factors

agent-desktop · 13

Score v2 uses observed signals only. Missing factors read No signal yet.

  • GitHub healthNo signal yet
  • Agent useNo signal yet
  • Human notesNo signal yet
  • ComposabilityNo signal yet
  • Checklist10.0 pts
  • Evidence quality2.5 pts
  • BenchmarksNo signal yet
Full Score explanation
Observed signals only

An MCP server using Playwright to let AI models visually analyze, automate, test, and debug web interfaces.

Function

Connect

speak a protocol (MCP, API, CLI)

Connect Browse Connect

Function

Browser

operate a live page

Browser Browse Browser

Function

Crawl

walk the public web

Crawl Browse Crawl

Function

Extract

pull a fact or field out

Extract Browse Extract

Function

Index

make retrieval cheap

Index Browse Index

Interface

mcp

Model Context Protocol server

Matched agent

GitHub

No signal yet

Agent use

No signal yet

Reputation

Human and agent evidence, together.

Score factors

VUDA (Visual UI Debug Agent) · 6

Score v2 uses observed signals only. Missing factors read No signal yet.

  • GitHub healthNo signal yet
  • Agent useNo signal yet
  • Human notesNo signal yet
  • ComposabilityNo signal yet
  • Checklist3.3 pts
  • Evidence quality2.5 pts
  • BenchmarksNo signal yet
Full Score explanation
Observed signals only
resourceseed
Agentation

Agentation is a visual feedback layer for agents working on web UIs. Humans click elements, annotate, optionally use layout mode (rearrange/resize), then copy structured markdown (or push via MCP/webhooks) so the agent gets element paths, CSS selectors, positions, and related context instead of vague prose.

Function

Connect

speak a protocol (MCP, API, CLI)

Connect Browse Connect

Interface

mcp

Model Context Protocol server

Matched agent

GitHub

Observed

Agent use

No signal yet

Reputation

Human and agent evidence, together.

Score factors

Agentation · 9

Score v2 uses observed signals only. Missing factors read No signal yet.

  • GitHub health2.7 pts
  • Agent useNo signal yet
  • Human notesNo signal yet
  • ComposabilityNo signal yet
  • Checklist3.3 pts
  • Evidence quality3.2 pts
  • BenchmarksNo signal yet
Full Score explanation
Observed signals only
agentseed
Sitegeist

Sitegeist is an AI assistant that lives in a Chromium side panel, plus a bridge so coding agents can use the same browser. README framing: collaboration over “autonomy theater” — you guide, it executes. Automates repetitive web tasks, extraction, navigation, forms, research → docs/spreadsheets; BYO API key or subscription login (Anthropic, OpenAI/ChatGPT, GitHub Copilot, Gemini, etc.); claims local-only / no tracking.

Function

Code

write or edit programs

Code Browse Code

Function

Browser

operate a live page

Browser Browse Browser

Function

Extract

pull a fact or field out

Extract Browse Extract

Interface

mcp

Model Context Protocol server

Interface

cli

Command-line interface

Matched agent

GitHub

Observed

Agent use

No signal yet

Reputation

Human and agent evidence, together.

Score factors

Sitegeist · 10

Score v2 uses observed signals only. Missing factors read No signal yet.

  • GitHub health2.7 pts
  • Agent useNo signal yet
  • Human notesNo signal yet
  • ComposabilityNo signal yet
  • Checklist3.3 pts
  • Evidence quality3.7 pts
  • BenchmarksNo signal yet
Full Score explanation
Observed signals only
appseed
Firecrawl

Crawl and extract clean page content for LLM pipelines. A common agent research tool and a Leyline evidence source class.

Function

Crawl

walk the public web

Crawl Browse Crawl

Function

Extract

pull a fact or field out

Extract Browse Extract

Function

Ingest

bring raw material in

Ingest Browse Ingest

Function

Connect

speak a protocol (MCP, API, CLI)

Connect Browse Connect

Interface

mcp

Model Context Protocol server

Interface

http

HTTP API

Matched agent

GitHub

Observed

Agent use

No signal yet

Reputation

Human and agent evidence, together.

Score factors

Firecrawl · 23

Score v2 uses observed signals only. Missing factors read No signal yet.

  • GitHub health5.4 pts
  • Agent useNo signal yet
  • Human notes1.2 pts
  • ComposabilityNo signal yet
  • Checklist10.0 pts
  • Evidence quality6.5 pts
  • BenchmarksNo signal yet
Full Score explanation
Observed signals only
appseed
TinyFish

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.

Function

Crawl

walk the public web

Crawl Browse Crawl

Function

Extract

pull a fact or field out

Extract Browse Extract

Function

Browser

operate a live page

Browser Browse Browser

Function

Connect

speak a protocol (MCP, API, CLI)

Connect Browse Connect

Interface

mcp

Model Context Protocol server

Interface

http

HTTP API

Matched agent

GitHub

Observed

Agent use

No signal yet

Reputation

Human and agent evidence, together.

Score factors

TinyFish · 23

Score v2 uses observed signals only. Missing factors read No signal yet.

  • GitHub health5.4 pts
  • Agent useNo signal yet
  • Human notes1.2 pts
  • ComposabilityNo signal yet
  • Checklist10.0 pts
  • Evidence quality6.8 pts
  • BenchmarksNo signal yet
Full Score explanation
Observed signals only
runtimeseed
Grok (xAI)

Reasoning and tool-using models plus a CLI harness. Leyline's own intake processor runs on the Grok Heavy subscription.

Function

Generate

produce new text, code, or media

Generate Browse Generate

Function

Reason

plan or chain steps

Reason Browse Reason

Function

Code

write or edit programs

Code Browse Code

Function

Tool-call

invoke an external action

Tool-call Browse Tool-call

Interface

mcp

Model Context Protocol server

Interface

http

HTTP API

Matched agent

GitHub

Observed

Agent use

No signal yet

Reputation

Human and agent evidence, together.

Score factors

Grok (xAI) · 21

Score v2 uses observed signals only. Missing factors read No signal yet.

  • GitHub health5.4 pts
  • Agent useNo signal yet
  • Human notes1.2 pts
  • ComposabilityNo signal yet
  • Checklist10.0 pts
  • Evidence quality4.6 pts
  • BenchmarksNo signal yet
Full Score explanation
Observed signals only
appseed
Exa

Neural web search API aimed at agents. Search slice with citations, distinct from crawl-the-page tools.

Function

Retrieve

fetch stored knowledge

Retrieve Browse Retrieve

Function

Extract

pull a fact or field out

Extract Browse Extract

Function

Connect

speak a protocol (MCP, API, CLI)

Connect Browse Connect

Function

Crawl

walk the public web

Crawl Browse Crawl

Interface

mcp

Model Context Protocol server

Interface

http

HTTP API

Matched agent

GitHub

Observed

Agent use

No signal yet

Reputation

Human and agent evidence, together.

Score factors

Exa · 18

Score v2 uses observed signals only. Missing factors read No signal yet.

  • GitHub health5.4 pts
  • Agent useNo signal yet
  • Human notesNo signal yet
  • ComposabilityNo signal yet
  • Checklist10.0 pts
  • Evidence quality2.5 pts
  • BenchmarksNo signal yet
Full Score explanation
Observed signals only
runtimeseed
Claude Code

Anthropic's terminal coding agent. Harness grid deep-link target for the Leyline scour skill.

Function

Code

write or edit programs

Code Browse Code

Function

Reason

plan or chain steps

Reason Browse Reason

Function

Tool-call

invoke an external action

Tool-call Browse Tool-call

Function

Connect

speak a protocol (MCP, API, CLI)

Connect Browse Connect

Function

Compose

assemble other functions

Compose Browse Compose

Interface

mcp

Model Context Protocol server

Interface

http

HTTP API

Matched agent

GitHub

Observed

Agent use

No signal yet

Reputation

Human and agent evidence, together.

Score factors

Claude Code · 15

Score v2 uses observed signals only. Missing factors read No signal yet.

  • GitHub health2.7 pts
  • Agent useNo signal yet
  • Human notesNo signal yet
  • ComposabilityNo signal yet
  • Checklist10.0 pts
  • Evidence quality2.5 pts
  • BenchmarksNo signal yet
Full Score explanation
Observed signals only
runtimeseed
Codex

OpenAI coding agent / CLI. Another day-one harness on the Leyline install grid.

Function

Code

write or edit programs

Code Browse Code

Function

Reason

plan or chain steps

Reason Browse Reason

Function

Tool-call

invoke an external action

Tool-call Browse Tool-call

Function

Connect

speak a protocol (MCP, API, CLI)

Connect Browse Connect

Interface

mcp

Model Context Protocol server

Interface

http

HTTP API

Matched agent

GitHub

Observed

Agent use

No signal yet

Reputation

Human and agent evidence, together.

Score factors

Codex · 15

Score v2 uses observed signals only. Missing factors read No signal yet.

  • GitHub health2.7 pts
  • Agent useNo signal yet
  • Human notesNo signal yet
  • ComposabilityNo signal yet
  • Checklist10.0 pts
  • Evidence quality2.5 pts
  • BenchmarksNo signal yet
Full Score explanation
Observed signals only

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.

Function

Connect

speak a protocol (MCP, API, CLI)

Connect Browse Connect

Function

Monitor

alert on drift

Monitor Browse Monitor

Interface

mcp

Model Context Protocol server

Interface

cli

Command-line interface

Interface

http

HTTP API

Interface

sdk

Language SDK

Matched agent

GitHub

Observed

Agent use

No signal yet

Reputation

Human and agent evidence, together.

Score factors

World Monitor · 14

Score v2 uses observed signals only. Missing factors read No signal yet.

  • GitHub health2.7 pts
  • Agent useNo signal yet
  • Human notesNo signal yet
  • ComposabilityNo signal yet
  • Checklist6.7 pts
  • Evidence quality4.3 pts
  • BenchmarksNo signal yet
Full Score explanation
Observed signals only
runtimeseed
Cursor

Agentic editor harness. A day-one Leyline install target: scour skill via MCP or rule file.

Function

Code

write or edit programs

Code Browse Code

Function

Reason

plan or chain steps

Reason Browse Reason

Function

Tool-call

invoke an external action

Tool-call Browse Tool-call

Function

Connect

speak a protocol (MCP, API, CLI)

Connect Browse Connect

Function

Retrieve

fetch stored knowledge

Retrieve Browse Retrieve

Interface

mcp

Model Context Protocol server

Matched agent

GitHub

Observed

Agent use

No signal yet

Reputation

Human and agent evidence, together.

Score factors

Cursor · 12

Score v2 uses observed signals only. Missing factors read No signal yet.

  • GitHub health2.7 pts
  • Agent useNo signal yet
  • Human notesNo signal yet
  • ComposabilityNo signal yet
  • Checklist6.7 pts
  • Evidence quality2.5 pts
  • BenchmarksNo signal yet
Full Score explanation
Observed signals only
mcpseed
Executor

Landing hero: Connect any agent to everything. Tagline: The gateway to connect your agent to everything. Page: Executor is an MCP gateway. Anything that speaks MCP, like Claude Code, Cursor, or Codex, points at one endpoint and reaches every tool you connect.

Function

Code

write or edit programs

Code Browse Code

Function

Connect

speak a protocol (MCP, API, CLI)

Connect Browse Connect

Interface

mcp

Model Context Protocol server

Matched agent

GitHub

Observed

Agent use

No signal yet

Reputation

Human and agent evidence, together.

Score factors

Executor · 12

Score v2 uses observed signals only. Missing factors read No signal yet.

  • GitHub health5.4 pts
  • Agent useNo signal yet
  • Human notesNo signal yet
  • ComposabilityNo signal yet
  • Checklist3.3 pts
  • Evidence quality3.2 pts
  • BenchmarksNo signal yet
Full Score explanation
Observed signals only
resourceintake
MCP / AI Gateway

Gateway layer that routes model calls, discovers MCP tools, and applies identity, policy, and spend controls before invocations.

Function

Route

send work to the right tool

Route Browse Route

Function

Auth

prove identity or permission

Auth Browse Auth

Function

Identity

name a person, agent, or org

Identity Browse Identity

Function

Policy

allow, deny, or bound an action

Policy Browse Policy

Function

Tool-call

invoke an external action

Tool-call Browse Tool-call

Interface

mcp

Model Context Protocol server

Interface

http

HTTP API

Matched agent

GitHub

No signal yet

Agent use

No signal yet

Reputation

Human and agent evidence, together.

Score factors

MCP / AI Gateway · 12

Score v2 uses observed signals only. Missing factors read No signal yet.

  • GitHub healthNo signal yet
  • Agent useNo signal yet
  • Human notes1.2 pts
  • ComposabilityNo signal yet
  • Checklist6.7 pts
  • Evidence quality4.6 pts
  • BenchmarksNo signal yet
Full Score explanation
Observed signals only
appintake
ElevenLabs

Developer interfaces for speech generation, transcription, audio and voice-agent workflows.

Function

Generate

produce new text, code, or media

Generate Browse Generate

Function

Transcribe

speech to text

Transcribe Browse Transcribe

Function

Telephony

place or take phone calls and text messages

Telephony Browse Telephony

Interface

http

HTTP API

Open spec

Interface

sdk

Language SDK

Open spec

Interface

mcp

Model Context Protocol server

Open spec

Matched agent

GitHub

No signal yet

Agent use

No signal yet

Reputation

Human and agent evidence, together.

Score factors

ElevenLabs · 10

Score v2 uses observed signals only. Missing factors read No signal yet.

  • GitHub healthNo signal yet
  • Agent useNo signal yet
  • Human notesNo signal yet
  • ComposabilityNo signal yet
  • Checklist6.7 pts
  • Evidence quality3.2 pts
  • BenchmarksNo signal yet
Full Score explanation
Observed signals only
runtimeintake
cognee

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.

Function

Memory

keep context across turns

Memory Browse Memory

Function

Code

write or edit programs

Code Browse Code

Function

Connect

speak a protocol (MCP, API, CLI)

Connect Browse Connect

Function

Embed

turn content into vectors

Embed Browse Embed

Function

Retrieve

fetch stored knowledge

Retrieve Browse Retrieve

Interface

mcp

Model Context Protocol server

Interface

http

HTTP API

Matched agent

GitHub

No signal yet

Agent use

No signal yet

Reputation

Human and agent evidence, together.

Score factors

cognee · 9

Score v2 uses observed signals only. Missing factors read No signal yet.

  • GitHub healthNo signal yet
  • Agent useNo signal yet
  • Human notesNo signal yet
  • ComposabilityNo signal yet
  • Checklist6.7 pts
  • Evidence quality2.5 pts
  • BenchmarksNo signal yet
Full Score explanation
Observed signals only
skillintake
ffmpeg-skill

Local media-editing tools and an agent skill with a machine-readable contract and MCP server.

Function

Transform

reshape data

Transform Browse Transform

Function

Render

draw a visual surface

Render Browse Render

Function

Transcribe

speech to text

Transcribe Browse Transcribe

Interface

cli

Command-line interface

Open spec

Interface

skill

Agent skill file

Open spec

Interface

mcp

Model Context Protocol server

Open spec

Matched agent

GitHub

No signal yet

Agent use

No signal yet

Reputation

Human and agent evidence, together.

Score factors

ffmpeg-skill · 9

Score v2 uses observed signals only. Missing factors read No signal yet.

  • GitHub healthNo signal yet
  • Agent useNo signal yet
  • Human notesNo signal yet
  • ComposabilityNo signal yet
  • Checklist6.7 pts
  • Evidence quality2.5 pts
  • BenchmarksNo signal yet
Full Score explanation
Observed signals only
mcpintake
memini

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.

Function

Connect

speak a protocol (MCP, API, CLI)

Connect Browse Connect

Function

Code

write or edit programs

Code Browse Code

Function

Compose

assemble other functions

Compose Browse Compose

Function

Deploy

put software into a runtime

Deploy Browse Deploy

Function

Memory

keep context across turns

Memory Browse Memory

Interface

mcp

Model Context Protocol server

Interface

http

HTTP API

Matched agent

GitHub

No signal yet

Agent use

No signal yet

Reputation

Human and agent evidence, together.

Score factors

memini · 9

Score v2 uses observed signals only. Missing factors read No signal yet.

  • GitHub healthNo signal yet
  • Agent useNo signal yet
  • Human notesNo signal yet
  • ComposabilityNo signal yet
  • Checklist6.7 pts
  • Evidence quality2.5 pts
  • BenchmarksNo signal yet
Full Score explanation
Observed signals only
resourceseed
REA

README tagline: "One MCP for reverse engineering across binaries, applications, and runtime behavior." The agent calls REA through MCP to inspect a local target and trace relevant code; REA returns findings with their evidence, and the agent uses them to explain the behavior or write and test an implementation.

Function

Code

write or edit programs

Code Browse Code

Function

Test

prove behavior

Test Browse Test

Function

Connect

speak a protocol (MCP, API, CLI)

Connect Browse Connect

Interface

mcp

Model Context Protocol server

Interface

cli

Command-line interface

Matched agent

GitHub

No signal yet

Agent use

No signal yet

Reputation

Human and agent evidence, together.

Score factors

REA · 7

Score v2 uses observed signals only. Missing factors read No signal yet.

  • GitHub healthNo signal yet
  • Agent useNo signal yet
  • Human notesNo signal yet
  • ComposabilityNo signal yet
  • Checklist3.3 pts
  • Evidence quality3.7 pts
  • BenchmarksNo signal yet
Full Score explanation
Observed signals only

A locally run MCP browser agent and optional web UI that automates a stealth Firefox browser for web browsing, scraping, and page interaction.

Function

Browser

operate a live page

Browser Browse Browser

Function

Code

write or edit programs

Code Browse Code

Function

Identity

name a person, agent, or org

Identity Browse Identity

Function

Policy

allow, deny, or bound an action

Policy Browse Policy

Interface

mcp

Model Context Protocol server

Matched agent

GitHub

No signal yet

Agent use

No signal yet

Reputation

Human and agent evidence, together.

Score factors

Invisible Playwright MCP · 6

Score v2 uses observed signals only. Missing factors read No signal yet.

  • GitHub healthNo signal yet
  • Agent useNo signal yet
  • Human notesNo signal yet
  • ComposabilityNo signal yet
  • Checklist3.3 pts
  • Evidence quality2.5 pts
  • BenchmarksNo signal yet
Full Score explanation
Observed signals only

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.

Function

Connect

speak a protocol (MCP, API, CLI)

Connect Browse Connect

Function

Memory

keep context across turns

Memory Browse Memory

Function

Code

write or edit programs

Code Browse Code

Function

Embed

turn content into vectors

Embed Browse Embed

Function

Extract

pull a fact or field out

Extract Browse Extract

Interface

mcp

Model Context Protocol server

Matched agent

GitHub

No signal yet

Agent use

No signal yet

Reputation

Human and agent evidence, together.

Score factors

Local FAISS MCP Server · 6

Score v2 uses observed signals only. Missing factors read No signal yet.

  • GitHub healthNo signal yet
  • Agent useNo signal yet
  • Human notesNo signal yet
  • ComposabilityNo signal yet
  • Checklist3.3 pts
  • Evidence quality2.5 pts
  • BenchmarksNo signal yet
Full Score explanation
Observed signals only
mcpintake
Lore

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

Function

Memory

keep context across turns

Memory Browse Memory

Function

Extract

pull a fact or field out

Extract Browse Extract

Function

Store

persist state

Store Browse Store

Function

Connect

speak a protocol (MCP, API, CLI)

Connect Browse Connect

Interface

mcp

Model Context Protocol server

Matched agent

GitHub

No signal yet

Agent use

No signal yet

Reputation

Human and agent evidence, together.

Score factors

Lore · 6

Score v2 uses observed signals only. Missing factors read No signal yet.

  • GitHub healthNo signal yet
  • Agent useNo signal yet
  • Human notesNo signal yet
  • ComposabilityNo signal yet
  • Checklist3.3 pts
  • Evidence quality2.5 pts
  • BenchmarksNo signal yet
Full Score explanation
Observed signals only

Evidence

Leyline ranks components. It does not proxy inference or resell tokens.

Human evidence

Observed stars, notes, maintainer trust, and public sources. Missing signals read No signal yet.

Agent evidence

Observed installs, success, resolve wins, and benches. Unobserved usage is never guessed or zeroed.