Refact.ai is an open-source, local-first AI coding assistant and autonomous software-engineering agent built by Small Magellanic Cloud Ai Ltd. ("SmallCloud"). The product combines an IDE-integrated chat experience (Ask / Explore / Debug / Review / Plan modes), accurate code completion powered by Qwen2.5-Coder with RAG over the workspace, and the Refact Agent — an autonomous mode that plans, executes, and iterates on engineering tasks end-to-end, integrating with Git hosts, databases, shells, browsers, and MCP servers. The full agent stack — a Rust HTTP/LSP engine (`refact-lsp`), a React/Vite chat GUI, and VS Code + JetBrains plugins — is open source under BSD-3-Clause at github.com/smallcloudai/refact and ranked #1 open-source agent on SWE-bench Lite (60.0%) and 93.3% on Aider's Polyglot benchmark with thinking mode. Refact supports a cloud SaaS tier (Free / Pro / Enterprise) — though Refact Cloud is being wound down in favor of BYOK + self-hosting — plus enterprise on-premise deployment with LLM fine-tuning, AWS Marketplace listings, and bring-your-own-key access to Anthropic, OpenAI, Google, xAI, DeepSeek, Groq, Ollama, LM Studio, vLLM, GitHub Copilot, and any OpenAI-compatible endpoint. Refact is positioned as a privacy-preserving, self-hostable alternative to closed cloud coding agents — workspace context, checkpoints, knowledge graphs, and trajectories are stored locally; no code is sent to the vendor's servers in self-hosted mode.
Refact.ai is listed with 2 APIs on the APIs.io network. Tagged areas include Artificial Intelligence, Coding Assistant, AI Agents, Autonomous Agents, and Code Completion.
Refact.ai’s developer surface includes developer portal, documentation, getting-started guide, pricing, engineering blog, signup flow, YouTube channel, and 23 more developer resources.
12.6/100emerging▬ flatAgent0/100human onlyFront door AI6/6
dominant
saas · BSD-3-Clause (Refact open-source components)
Full breakdown ↓
scored 2026-10-23 · rubric v0.25.0 · Show this score on your site →
Regulatory Posture applies to this provider. Its tags matched the
Horizontal (data, software, accessibility, platform) regime, so
Regulatory Posture carries 15 points of the composite.
If this regime is wrong for your business, say so on your
provider repo — the
applicability map is public and we will correct it.
Create-or-Update Ergonomics could not be measured. We hold no machine-readable contract for
this provider to read, so there is nothing to measure a write surface against. Excluded rather than scored zero:
never-measured and measured-empty are different facts. Publishing an OpenAPI is what makes this facet — and
several others — scorable at all.
The six quality facets above are damped to 85 points between them,
because the conditional facet above carries the other
15. That is why each facet's contribution is shown against a damped
maximum: raising a quality facet moves the composite by 85% of its nominal
weight, not 100%. The full arithmetic is at apis.io/rating/.
Show this score on your site.
It updates itself when the score changes. Paste this where you link to your API docs:
<a href="https://apis.io/providers/refact-ai/"><img src="https://apis.io/badge/refact-ai/card.svg" alt="Refact.ai on APIs.io — Kin Score by API Evangelist"></a>
Other styles, a README pill and a shields.io endpoint are on the badge page.
Improve this rating by publishing the missing artifacts — every area above can be raised, and the full rubric is at apis.io/rating/. Every facet and dimension name above is a link: it opens that measurement's own page — what it means, the exact checks that feed it, how the whole catalog distributes on it, and the providers at the top of it. This rating is computed from github.com/api-evangelist/refact-ai: open an issue to ask a question, or submit a pull request to add artifacts.
Submit an artifact on GitHub — free →Manage your own listing — the Influence plan, $499/mo →
Markets this provider is in provisional
The Kin Score Market layer reads a provider inside its market:
its position, and how deep its integrations go. Depth is only comparable within a position. Provisional and unweighted:
not part of the Kin Score or agent readiness.
Registered MCP server and declares compatibility are report only — not weighted.
Undeclared means we found nothing we can read, so there is no number: we never infer integrations.
Standards this provider implements or carries. De facto ones are profiled and measured by the API Commons; formal ones come from the standards directory and are linked by the provider's own tags. The evidence column says how each claim was established — not that it was made.
Local HTTP/LSP API exposed by the Rust `refact-lsp` engine that runs inside the user's IDE or as a standalone server. Implements the agent runtime: provider/model capabilities, ...
Refact Agent acts as an MCP (Model Context Protocol) client, attaching local or remote MCP servers (`npx`, Python `-m`, `docker run`, or remote SSE) into the agent's tool surfac...
Discovery needs no key. Ratings and market analysis are Pro.
Get an API key
Free tier, no form to fill in. Signing in shares your email address with us — we
store it to create your key and to recognise you if you sign in with another
provider. See our Privacy Policy and
Terms.
Kin Score
How this is scored →
It updates itself when the score changes. Paste this where you link to your API docs: