Refact.ai

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 publishes 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.

🌐 Visit website 📡 Source on GitHub

12.6/100 emerging ▬ flat Agent 0/100 human only Front door AI 6/6 dominant saas · BSD-3-Clause (Refact open-source components) Full breakdown ↓
scored 2026-10-04 · rubric v0.23.0

2 APIs 23 Features

Artificial Intelligence Coding Assistant AI Agents Autonomous Agents Code Completion Code Generation Developer Tools IDE VS Code JetBrains Self-Hosting On-Premises Open Source LSP MCP Fine-TuningSWE-BenchRAG

Kin Score

Kin Score How this is scored →
scored 2026-10-04 · rubric v0.23.0

Composite quality — 12.6/100 · emerging

Contract Quality 0.0 / 21

Developer Ergonomics 2.8 / 17

Access Clarity 2.2 / 17

Operational Transparency 2.0 / 11

Contract Governance 0.0 / 10

Discoverability 4.9 / 9

Regulatory Posture 0.8 / 15

Agent readiness — 0/100 · human only

Machine-Readable Contract 0 / 18

Agentic Access Contract 0 / 10

Documented Reversibility 0 / 6

MCP Server 0 / 12

Machine-Readable Auth 0 / 10

Idempotency 0 / 9

Stable Error Semantics 0 / 8

Request/Response Examples 0 / 7

Rate-Limit Signaling 0 / 7

Typed Event Surface 0 / 6

Agent Skills 0 / 5

Well-Known Catalog 0 / 4

Consent & Bot Identity 0 / 3

A2A Agent Card 0 / 8

Dry-Run / Simulate Mode 0 / 4

Delegated User Identity 0 / 6

Protected Resource Metadata 0 / 5

Registration Without a Human 0 / 6

Agentic Commerce Well-Known Document 0 / 5

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/.

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 →

Standards implemented 1

Interfaces this provider implements that became standards by being copied rather than ratified. Each is profiled by the API Commons, and the evidence column says how the claim was established — not that it was made.

The OpenAI Interface

prose — states compatibility; nothing published to check it against

2 core of 338 operations graded · api-commons/models

APIs 2

Individual APIs this provider publishes, each with its own machine-readable definition.

Refact Agent Engine API

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 MCP Integration

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...

Features 23

Notable capabilities this provider offers.

Refact Agent — autonomous IDE agent that plans, executes, and iterates

Agent modes — Ask, Explore, Debug, Review, Plan, Agent

In-IDE chat with context-aware code understanding

Real-time code completion powered by Qwen2.5-Coder + RAG over the workspace

25+ programming languages including Python, JavaScript/TypeScript, Java, Go, Rust, PHP, C#, Ruby, Kotlin, Swift

Local-first execution — workspace context, checkpoints, knowledge, and trajectories stored locally

Open-source agent stack under BSD-3-Clause (Rust engine + React GUI + IDE plugins)

VS Code, JetBrains (IntelliJ, PyCharm, WebStorm, GoLand, CLion), Visual Studio, Neovim, Sublime Text plugins

MCP (Model Context Protocol) client — attach any local or remote MCP server as agent tools

Built-in tool integrations — GitHub, GitLab, Bitbucket, Docker, Chrome, Shell, PostgreSQL, MySQL, PDB

Workspace checkpoints and one-click rollback for agent operations

Knowledge graph and long-term memory across agent sessions

Bring-Your-Own-Key for Anthropic, OpenAI, Google Gemini, xAI Grok, DeepSeek, Groq, OpenRouter, GitHub Copilot

Local model providers — Ollama, LM Studio, vLLM, custom OpenAI-compatible endpoints

LLM fine-tuning on company codebase (Refact, StarCoder, DeepSeek-Coder, CodeLlama variants)

Enterprise on-premise deployment with full code privacy

AWS Marketplace listing — EC2 deployment and usage-based pricing

Runpod and reverse-proxy deployment recipes

Image-to-code, code review, and AI Toolbox features

Confirmation rules to block or prompt before sensitive tool/MCP calls

93.3% on Aider Polyglot benchmark with thinking mode

Coin-based usage metering on the cloud tier (replacing per-request limits)

Scroll for all 23

Security Posture 1

Authentication, domain security, vulnerability disclosure, and trust-center signals.

Refact Ai Domain Security

TLSv1.3 · HSTS · DMARC

SECURITY

Resources

Get Started 4

Portal, sign-up, and the first successful call

Portal

Portal

GettingStarted

GettingStarted

Signup

Signup

Login

Documentation 2

Reference material describing how the API behaves

ContributionGuide

ContributionGuide

Documentation

Documentation

Build 9

SDKs, sample code, and the tooling you integrate with

GitHubOrganization

SourceCode

SourceCode

SourceCode

SourceCode

SourceCode

SourceCode

IDEExtension

IDEExtension

Scroll for all 9

Access & Security 1

Authentication, authorization, and security posture

DomainSecurity

DomainSecurity

Learn 1

Tutorials, courses, talks, and written guidance

YouTube

YouTube

Operate 4

Status, limits, changes, and where to get help

IssueTracker

Releases

Contact

Discord

Commercial 3

Pricing, plans, and the legal terms of use

Pricing

Pricing

Plans

Plans

License

License

Company 4

The organization behind the API

Website

Website

Blog

Blog

Twitter

Twitter

LinkedIn

Other 2

Properties that don't map to a standard resource type

Enterprise

Enterprise

AWSMarketplace

AWSMarketplace

Source (apis.yml)

aid: refact-ai
name: Refact.ai
description: '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.'
type: Index
deliveryModel:
  model: saas
  license: BSD-3-Clause (Refact open-source components)
  open_source: false
  commercial: true
  callable_host: false
  label: Hosted service · you call their endpoint
  confidence: medium
  source:
  - license
  - pricing
  generated: '2026-08-28'
  method: derived
accessModel:
  pricing: unknown
  onboarding: unknown
  trial: false
  try_now: false
  public: false
  label: Unknown
  confidence: low
  source: []
  generated: '2026-07-22'
  method: derived
position: Producing
access: 3rd-Party
kind: contract
image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/icons/refact-ai.png
tags:
- Artificial Intelligence
- Coding Assistant
- AI Agents
- Autonomous Agents
- Code Completion
- Code Generation
- Developer Tools
- IDE
- VS Code
- JetBrains
- Self-Hosting
- On-Premises
- Open Source
- LSP
- MCP
- Fine-Tuning
- SWE-Bench
- RAG
tags_raw:
- AI
- Artificial Intelligence
- Coding Assistant
- AI Agent
- Autonomous Agents
- Code Completion
- Code Generation
- Developer Tools
- IDE
- VS Code
- JetBrains
- Self-Hosting
- On-Premise
- Open Source
- LSP
- MCP
- Model Context Protocol
- Fine-Tuning
- SWE-Bench
- RAG
- Open-Source
url: https://raw.githubusercontent.com/api-evangelist/refact-ai/refs/heads/main/apis.yml
created: '2026-05-25'
modified: '2026-05-25'
specificationVersion: '0.23'
apis:
- aid: refact-ai:refact-engine-api
  name: Refact Agent Engine API
  description: '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, chat command queueing, SSE event streams, code completion,
    tool registry and confirmation rules, AST indexing, RAG/vector search over the workspace, integrations configuration,
    knowledge graph operations, task board management, and workspace checkpoint/rollback. This is the contract the VS Code
    and JetBrains plugins and the GUI call over `http://127.0.0.1:<port>/v1`.'
  humanURL: https://docs.refact.ai
  tags:
  - Artificial Intelligence
  - Agents
  - LSP
  - HTTP
  - Local
  tags_raw:
  - AI
  - Agent
  - LSP
  - HTTP
  - Local
  properties:
  - url: https://docs.refact.ai
    type: Documentation
  - url: https://github.com/smallcloudai/refact/tree/main/refact-agent/engine
    type: SourceCode
  - url: https://github.com/smallcloudai/refact
    type: GitHubRepository
- aid: refact-ai:refact-mcp-integration
  name: Refact MCP Integration
  description: 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 surface with per-tool confirmation rules. This makes any
    MCP server an extension of the Refact Agent's capability set inside the IDE.
  humanURL: https://docs.refact.ai/features/autonomous-agent/integrations/mcp/
  tags:
  - MCP
  - Agents
  - Integration
  tags_raw:
  - MCP
  - Model Context Protocol
  - Agent
  - Integrations
  properties:
  - url: https://docs.refact.ai/features/autonomous-agent/integrations/mcp/
    type: Documentation
  - url: https://github.com/modelcontextprotocol
    type: Standards
common:
- type: IssueTracker
  url: https://github.com/smallcloudai/refact/issues
- type: Releases
  url: https://github.com/smallcloudai/refact/releases
- type: ContributionGuide
  url: https://github.com/smallcloudai/refact/blob/main/CONTRIBUTING.md
- type: DomainSecurity
  url: security/refact-ai-domain-security.yml
- type: Website
  url: https://refact.ai
- type: Portal
  url: https://refact.ai
- type: Documentation
  url: https://docs.refact.ai
- type: GettingStarted
  url: https://docs.refact.ai/introduction/quickstart/
- type: Enterprise
  url: https://refact.ai/enterprise/
- type: Pricing
  url: https://refact.ai/pricing
- type: Plans
  url: https://refact.ai/pricing
- type: Blog
  url: https://refact.ai/blog/
- type: Signup
  url: https://refact.smallcloud.ai/
- type: Login
  url: https://refact.smallcloud.ai/
- type: Contact
  url: https://refact.ai/contact/
- type: GitHubOrganization
  url: https://github.com/smallcloudai
- type: SourceCode
  name: Refact (monorepo — engine, GUI, plugins, docs)
  url: https://github.com/smallcloudai/refact
- type: SourceCode
  name: refact-vscode (archived — now in monorepo)
  url: https://github.com/smallcloudai/refact-vscode
- type: SourceCode
  name: refact-intellij (archived — now in monorepo)
  url: https://github.com/smallcloudai/refact-intellij
- type: SourceCode
  name: refact-bench (SWE-Bench benchmarking harness)
  url: https://github.com/smallcloudai/refact-bench
- type: SourceCode
  name: rust-sdk (MCP Rust SDK fork)
  url: https://github.com/smallcloudai/rust-sdk
- type: SourceCode
  name: litellm (proxy fork)
  url: https://github.com/smallcloudai/litellm
- type: License
  name: BSD-3-Clause (Refact open-source components)
  url: https://github.com/smallcloudai/refact/blob/main/LICENSE
- type: IDEExtension
  name: Refact for VS Code
  url: https://marketplace.visualstudio.com/items?itemName=smallcloud.codify
- type: IDEExtension
  name: Refact for JetBrains
  url: https://plugins.jetbrains.com/plugin/20647-refact-ai
- type: AWSMarketplace
  url: https://aws.amazon.com/marketplace/seller-profile?id=seller-zb3svnusgaibm
- type: Discord
  url: https://www.smallcloud.ai/discord
- type: Twitter
  url: https://twitter.com/refact_ai
- type: LinkedIn
  url: https://www.linkedin.com/company/smallcloud
- type: YouTube
  url: https://www.youtube.com/@refactai
- type: Features
  data:
  - Refact Agent — autonomous IDE agent that plans, executes, and iterates
  - Agent modes — Ask, Explore, Debug, Review, Plan, Agent
  - In-IDE chat with context-aware code understanding
  - Real-time code completion powered by Qwen2.5-Coder + RAG over the workspace
  - 25+ programming languages including Python, JavaScript/TypeScript, Java, Go, Rust, PHP, C#, Ruby, Kotlin, Swift
  - Local-first execution — workspace context, checkpoints, knowledge, and trajectories stored locally
  - Open-source agent stack under BSD-3-Clause (Rust engine + React GUI + IDE plugins)
  - VS Code, JetBrains (IntelliJ, PyCharm, WebStorm, GoLand, CLion), Visual Studio, Neovim, Sublime Text plugins
  - MCP (Model Context Protocol) client — attach any local or remote MCP server as agent tools
  - Built-in tool integrations — GitHub, GitLab, Bitbucket, Docker, Chrome, Shell, PostgreSQL, MySQL, PDB
  - Workspace checkpoints and one-click rollback for agent operations
  - Knowledge graph and long-term memory across agent sessions
  - Bring-Your-Own-Key for Anthropic, OpenAI, Google Gemini, xAI Grok, DeepSeek, Groq, OpenRouter, GitHub Copilot
  - Local model providers — Ollama, LM Studio, vLLM, custom OpenAI-compatible endpoints
  - LLM fine-tuning on company codebase (Refact, StarCoder, DeepSeek-Coder, CodeLlama variants)
  - Enterprise on-premise deployment with full code privacy
  - AWS Marketplace listing — EC2 deployment and usage-based pricing
  - Runpod and reverse-proxy deployment recipes
  - Image-to-code, code review, and AI Toolbox features
  - Confirmation rules to block or prompt before sensitive tool/MCP calls
  - null
  - 93.3% on Aider Polyglot benchmark with thinking mode
  - Coin-based usage metering on the cloud tier (replacing per-request limits)
  sources:
  - https://refact.ai
  - https://refact.ai/enterprise/
  - https://refact.ai/pricing
  - https://docs.refact.ai
  - https://docs.refact.ai/supported-models/
  - https://docs.refact.ai/features/autonomous-agent/integrations/mcp/
  - https://github.com/smallcloudai/refact
  - https://refact.ai/blog/
  updated: '2026-05-25'
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com
  X: apievangelist
  url: https://apievangelist.com

Work with this as data

Every provider here is available over the APIs.io API and to AI agents over MCP.

MCP server

One button, every client — Claude, Cursor, VS Code and the rest.

https://apis.io/mcp

Tools for providers

9 MCP tools reach this

find_providersBrowse and filter every provider in the catalog.
get_provider_artifactsEvery artifact this provider publishes, grouped by type.
get_provider_operationsEvery operation across all of their OpenAPIs — one call instead of parsing every spec.
get_provider_toolsEvery MCP tool they ship, with the operation each wraps.
get_provider_evidenceHow each part of their score was established. Free — the basis for a claim should not sit behind it.
get_provider_ratingPRO — composite, band, trend and facet scores.
apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.
resolveTurn a domain, URL or GitHub org into the provider it belongs to.
find_cohortsEvery scored population of providers in the catalog.

All 92 tools →

Call it yourself

curl for this page

This provider

curl "https://apis.io/api/v1/providers/refact-ai"

All providers

curl "https://apis.io/api/v1/providers?limit=25"

Every operation they expose

curl "https://apis.io/api/v1/providers/refact-ai/operations?limit=25"

How their score was established

curl "https://apis.io/api/v1/providers/refact-ai/evidence"

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.

GitHub Google LinkedIn

A second provider on the same verified email joins the account you already have.