Enterprise DNAEnterprise DNA
The Enterprise DNA directoryIndependent choices. Original sources. ↗

Find your next
useful tool.

A clearer way to explore AI. Understand what a tool does, where it fits and how to get started.

↗

Less searching.
More knowing what to use.

Explore the collection ↓
Start with a taskCode ↗Data ↗Documents ↗Automation ↗Connections ↗Research ↗
01 / LEARN

Make something useful.

Start with spreadsheets, documents or a small workflow. Every reviewed guide includes a first task to try.

Find a starting point →02 / DECIDE

See the trade-offs.

Put up to three tools side by side. Compare who they suit, what they need and when to choose something else.

Compare tools →03 / EXPLORE

Understand your options.

Explore the wider model catalogue, pricing and context. Catalogue records and editorial reviews are clearly separated.

Browse models →

A small thing to learn · 5 minutes

Write a useful memo without inventing facts

Separate the facts you supplied from the details an assistant is tempted to add.

Try the exercise →

The editorial collection

A useful place to start.

Clear use cases, honest limitations and original documentation. Source reviews are separate from installation tests.

How we review ↗

29 reviewed tools

Choose up to 3 tools to compare · Saved on this device

Source reviewedAAgents

Claude Code

Anthropic

Work on a real codebase with an assistant that can inspect files, make changes and run commands.

View costs and setup

Best for: People maintaining a repository who want help with a specific change.

Source reviewedAAgents

Cursor

Anysphere

An editor with an integrated agent, useful when you want to see code and proposed changes together.

View costs and setup

Best for: People who prefer working inside an editor with visible files and changes.

Source reviewedMMCP✓ Official

GitHub MCP Server

GitHub

Give a compatible assistant structured access to repositories, issues and pull requests.

View costs and setup

Best for: Teams that want their assistant to work with GitHub context.

Source reviewedOOSS

FreeLLMAPI

Tashfeen Ahmed

A self-hosted router that puts the free tiers of dozens of model providers behind one OpenAI-compatible endpoint, using your own provider keys.

★ 29,899repo activity 29d ago94/100
View costs and setupTypeScript

Best for: Developers who want to try many models for free on their own machine through one endpoint and one key.

Source reviewedOOSS

Ollama

Ollama

Run supported language models on your computer, with additional cloud options.

★ 172,846repo activity 5mo ago
View costs and setupGo

Best for: People evaluating local models or building against a local model API.

Source reviewedOOSS

Dify

Dify

Build applications, agents and document-backed chat workflows through a visual platform.

★ 143,435repo activity 5mo ago
View costs and setupTypeScript

Best for: Teams prototyping a document assistant or model-backed workflow.

Source reviewedOOSS

LobeHub (formerly LobeChat)

LobeHub

A self-hostable chat and agent workspace, renamed from LobeChat to LobeHub in January 2026, that works with OpenAI, Anthropic, Google, OpenRouter, local Ollama and dozens of other providers.

★ 78,069repo activity 5mo ago
View costs and setupTypeScript

Best for: Individuals and teams who want one chat and agent app across many model providers, hosted or on their own server.

Source reviewedOOSS

Flowise

Flowise

Assemble agent and language-model workflows using a visual builder.

★ 53,254repo activity 5mo ago
View costs and setupTypeScript

Best for: Builders who want to inspect and change the steps of a model workflow.

Source reviewedOOSS

LiteLLM

BerriAI

A Python SDK and a self-hosted proxy, the LiteLLM AI Gateway, that let apps call more than 100 model providers through one OpenAI-format API, with virtual keys, budgets, fallbacks and spend tracking.

★ 48,950repo activity 5mo ago
View costs and setupPython

Best for: Platform teams running a shared gateway for several apps that need per-team keys, budgets and spend logs across providers.

Source reviewedOOSS

OrcaRouter Lite

Continuum AI

A self-hosted, single-workspace model router that accepts OpenAI, Anthropic and Gemini style requests and, in auto mode, picks the cheapest configured model that can handle each request.

★ 1,714repo activity 30d ago84/100
View costs and setupPython

Best for: Developers who want a small router with a local dashboard in front of their own provider keys.

Source reviewedOOSS

GoModel

Enterpilot

An open-source gateway written in Go that puts OpenAI, Anthropic, Gemini, Bedrock, Groq, OpenRouter, Ollama and other providers behind one OpenAI-compatible and Anthropic-compatible API.

★ 1,201repo activity 30d ago83/100
View costs and setupGo

Best for: Teams that want a self-hosted gateway with a dashboard, caching, failover, budgets and usage tracking across several providers.

Source reviewedOOSSObs

Helicone

Helicone

An LLM observability platform with an OpenAI-compatible gateway. It logs each request's cost, latency and errors, and routes calls to 100+ models with your own keys or prepaid credits.

★ 5,766repo activity 5mo ago
View costs and setupTypeScript

Best for: Teams that want request logs, cost tracking and prompt analytics for an LLM app, hosted or self-hosted.

Source reviewedOOSS

AISIX

API7.ai

An open-source gateway written in Rust, from the original creators of Apache APISIX, that puts one OpenAI-compatible and Anthropic-compatible API in front of OpenAI, Anthropic, Gemini, Bedrock, Azure OpenAI and other providers.

★ 177repo activity 29d ago77/100
View costs and setupRust

Best for: Platform teams that want a single-binary gateway with routing, failover, rate and token limits, guardrails and caching, configured from files.

Source reviewedOOSS

Plandex

PlandexAI

An open-source terminal coding agent for large, multi-file changes. Its company and cloud service wound down in October 2025, and the code has had no commits since.

★ 15,434repo activity 1y ago
View costs and setupGo

Best for: Developers who want to study or fork a coding agent that plans changes and holds them in a reviewable sandbox before applying them.

Source reviewedOOSS

Relay

Imamuzzaki Abu Salam

A small local proxy that lets coding agents such as Claude Code and Codex CLI switch between your GitHub Copilot, OpenAI, Anthropic, Z.AI, DeepSeek, Groq, Ollama and other accounts without a restart.

★ 10repo activity 4mo ago54/100
View costs and setupTypeScript

Best for: Developers with several provider accounts who want one local switch for their coding agent, on a machine only they use.

Source reviewedOOSS

Kunavo

Kunavo

A hosted, independent API gateway that resells access to Claude, GPT and image, video and music models through one key and a prepaid balance, with OpenAI-compatible and Anthropic Messages endpoints. It is not Anthropic and not open source.

View costs and setup

Best for: Independent developers who want Claude below Anthropic's list price for experiments and can live with outages.

Source reviewedPApps

n8n

n8n

Connect applications and transform data through visual workflows with optional code steps.

View costs and setup

Best for: Technical operators building repeatable integrations between business systems.

Source reviewedOOSS

TeamoRouter

Teamo HK Limited

A hosted, closed-source API gateway from Teamo HK Limited that gives coding agents such as Claude Code and Codex one key for Claude, GPT, Gemini, DeepSeek, GLM and other models, billed per token from a prepaid balance.

View costs and setup

Best for: Developers who want discounted per-token access to several model families for coding agents, and accept a Hong Kong reseller handling their prompts.

Source reviewedOOSS

TokenMix

Token Limited

A hosted API relay run by Token Limited in Hong Kong that resells access to Claude, OpenAI, Gemini, DeepSeek, Qwen and image, video and audio models through one OpenAI-compatible endpoint and a prepaid wallet. It is not open source.

View costs and setup

Best for: Developers who want one prepaid wallet across many model families, topped up in small amounts.

Source reviewedOOSS

UnoRouter

UnoRouter

A hosted service that resells access to more than 200 models from OpenAI, Anthropic, Google, DeepSeek, Qwen and others through one key, with OpenAI, Anthropic and Gemini style endpoints. Its code is public under the AGPL licence.

View costs and setup

Best for: Individuals who want cheap prepaid access to many models for personal coding or chat, and accept that requests may be served by third-party providers abroad.

Source reviewedAAgents

Aider

Aider contributors

A command-line coding assistant for making changes to files in a local Git project.

View costs and setup

Best for: Developers comfortable with a terminal who want to choose a supported model.

Source reviewedSSkills

DOCX Skill

Anthropic

Create and edit Word documents through a compatible assistant's file tools.

View costs and setup

Best for: Producing a structured .docx deliverable from supplied material.

Source reviewedMMCPBrowser✓ Official

Fetch MCP Server

Model Context Protocol contributors

Retrieve web content and convert it into text an assistant can process.

View costs and setup

Best for: Reading a known public URL without a full browser session.

Source reviewedMMCP✓ Official

Filesystem MCP Server

Model Context Protocol contributors

Give an MCP-compatible assistant file operations inside explicitly allowed directories.

View costs and setup

Best for: Working with a small local folder through an assistant that supports MCP.

Source reviewedMMCPBrowser✓ Official

Playwright MCP

Microsoft

Let a compatible assistant interact with a browser through Playwright tools.

View costs and setup

Best for: Builders inspecting and testing a web interface with an assistant.

Source reviewedSSkills

PDF Skill

Anthropic

A reference skill for processing PDF files, including extraction and document assembly.

View costs and setup

Best for: File-based PDF work in an assistant with the required tools.

Source reviewedSSkills

PPTX Skill

Anthropic

Instructions and tools for reading, editing and creating PowerPoint files.

View costs and setup

Best for: An assistant turning supplied content into an editable presentation file.

Source reviewedOOSS

Vercel AI Gateway

Vercel

A hosted gateway from Vercel that gives you one API key and one endpoint for hundreds of models, with OpenAI-compatible and Anthropic-compatible APIs, budgets, request logs and provider fallback. It is not open source.

View costs and setuptypescript

Best for: Developers who want one account for many models at provider list prices, from any server or local machine, without running a gateway themselves.

Source reviewedSSkills

XLSX Skill

Anthropic

Instructions and supporting tools for reading, editing and creating spreadsheet files.

View costs and setup

Best for: An assistant producing a workbook with formulas, formatting or cleaned data.

Looking beyond this collection?

Search the full catalogue →

Go deeper

The wider catalogue.

Browse by type. Imported records are discovery leads, not automatic recommendations.

Explore alternatives →
AAgents157 indexedSSkills2,815 indexedMMCP Servers29,656 indexedOOpen Source1,185 indexedPApps and SaaS293 indexedBBuilder Showcase5 indexedLModels1,412 indexed
Model Pulse· Oct 28 · since yesterday

1 new model, 7 price moves since yesterday.

Particle-1 just landed at $0.25/M in; GLM 5.3 Flash dropped 85.2% on price.

NEWParticle-1$0.25/M in▼ 85.2%GLM 5.3 Flashcheaper
1 new model5 price cuts
See what changed →

Keep learning

Tools make more sense in context.

Follow the developments behind the tools, then come back to choose what to try.

Read AI Pulse ↗