30 entries

The whole shelf

Every open-source building block in the atlas, in one flat list. Search by name or tag, or filter by category.

30 of 30 entries

INF·0124k agent A agent B a2a protocol

A2A

An open protocol that lets independent agents discover each other and collaborate across frameworks and vendors.

MITprotocolinterop
view source
SEC·02895 actions allow block

AgentShield

Adds guardrails and security checks around agents to catch unsafe or unintended actions.

MITguardrailssecurity
view source
LOC·0320k

AirLLM

Run 70B-parameter LLMs on a single 4GB GPU — AirLLM does layer-by-layer inference so huge models fit on modest hardware, with no quantization, distillation, or pruning required.

Apache-2.0pythonllminference
view source
CMP·04100k click · type · navigate

browser-use

Gives an agent control of a real browser so it can click, type, and navigate the web like a person.

MITbrowserautomation
view source
OPS·0516k tokens / day $12.40

ccusage

A small CLI that breaks down your Claude Code token usage and spend.

MITCLIcost
view source
DEV·06136k Claude pdfxlsxdocx

Claude Skills collection

A collection of reusable Claude skills you can plug in for common tasks.

MITskillsreusable
view source
INF·0729k hub

Composio

A tool layer that wires agents into hundreds of real apps and APIs with managed authentication.

MITintegrationsauthtools
view source
RAG·0858k docs v2.4.1 context

Context7

Feeds version-correct documentation for the libraries you're using straight into the model's context, via MCP.

MITMCPdocs
view source
AGT·0925k lead sub sub sub steps

DeepAgents

Scaffolding for long-horizon agents that plan, spin up sub-agents, and keep working across many steps.

MITframeworksub-agents
view source
DOC·1023k ocr few tokens

DeepSeek-OCR

A vision model that reads documents and compresses pages into very few tokens, making long PDFs cheap to feed a model.

MITOCRvision
view source
RAG·1117k repo

DeepWiki-open

Point it at any GitHub repo and it generates a browsable, navigable wiki that explains the codebase.

MITdocsrepos
view source
DOC·129.0k title fig table

Dolphin

Parses document images — tables, columns, figures — into clean structured layout for downstream use.

MITdoc-parsinglayout
view source
DAT·13135k site # - item

Firecrawl

Crawls entire sites and returns clean, LLM-ready markdown or structured JSON — the scraping workhorse behind many RAG pipelines.

MITscrapingmarkdownself-host
view source
DAT·1411k

Jina Reader

Point it at any URL and it hands back clean, model-ready text, stripping the page down to what matters.

MITreaderweb
view source
DOC·1537k name: date:

LangExtract

Uses an LLM to pull structured fields out of messy text, keeping each value linked back to where it came from.

MITPythonextraction
view source
OPS·1629k trace score

Langfuse

Open-source observability for LLM apps: trace every call, run evals, and watch cost and quality over time.

MITobservabilityevalstracing
view source
INF·176.9k

MCP Registry

The official directory of Model Context Protocol servers — a package index for agent tools.

MITMCPregistry
view source
INF·186.2k

NLWeb

Turns a website's own content into a conversational, agent-readable interface.

MITwebconversational
view source
AGT·1964k plan write run check

OpenHands

An open platform for software-building agents — hand it a task and it plans, writes code, runs commands, and browses the web until the work actually ships.

MITpythonagentsmodel-agnostic
view source
DEV·2056k spec.diff approve

OpenSpec

A spec-first workflow that keeps AI coding aligned to an agreed, reviewable specification.

MITspec-driven
view source
SEC·211.2k target probe

power-pwn

A red-team toolkit for probing Microsoft 365 Copilot and Power Platform — for security research, not production.

MITred-teamresearch
view source
SEC·229.0k Jane Doe <PERSON> a@mail.com <EMAIL> detect · redact

Presidio

Detects and redacts personal data — names, emails, IDs — in text and images; a natural partner to PromptMask.

MITPIIredaction
view source
SEC·23127 your prompt Jane Doe ${NAME_1} sk-9f2a…c01 ${KEY_1} filter cloud LLM

PromptMask

Local-first privacy layer for LLMs that redacts sensitive data before cloud API calls and restores it in responses.

MITpythonprivacypii
view source
AGT·2418k model out schema name: str age: int ok: bool

Pydantic-AI

An agent framework from the Pydantic team that brings type-safe, validated outputs to tool-calling agents.

MITPythonframeworktype-safe
view source
RAG·2583k document index query answer [1]

RAGFlow

Open-source RAG engine with deep document understanding, agent workflows, and production-ready ingestion pipelines.

Apache-2.0pythongorag
view source
DAT·2627k { "title": "price": "tags": }

ScrapeGraphAI

Python library for AI-powered web scraping — describe what you want extracted and let an LLM-driven graph pipeline handle the rest.

MITpythonscrapingllm
view source
DEV·27114k spec

Spec Kit

GitHub's toolkit for spec-driven development — write the spec first and let agents build to it.

MITspec-drivenworkflow
view source
DEV·2812k library testdocslint your agent docs

Subagents collection

A ready-made library of specialized sub-agents you can drop into your own agent setup.

MITsub-agentslibrary
view source
INF·2921k durable workflow s1s2s3s4 retry

Temporal

A durable execution engine that keeps long-running agent workflows reliable through retries, failures, and restarts.

MITworkflowsdurable
view source
CMP·3037k

UI-TARS Desktop

A GUI agent app that operates your actual computer — apps and windows — from natural-language instructions.

MITcomputer-useGUI
view source