Back to vendors
R

Refact.ai

Also known as: SmallCloud AI, Small Magellanic Cloud Ai Ltd

Visit site
Entry priceFree for personal and hobby projects, with limited daily agent use and unlimited completions. Pro is from $10 a month with 40 agent requests a day, and Enterprise is by contact. Hosted Refact Cloud is being retired with no final date published, and the open source local engine with the customer's own keys is free.Full pricing detail

Open-source, local-first autonomous coding agent that plans, edits, runs tests and iterates inside your IDE with a thirty-action cap, keeping AST and vector indexes locally and running on your own model keys or local runtimes. The hosted Refact Cloud service is being retired.

Refact.ai is an open-source, local-first autonomous coding agent that handles engineering tasks end to end from inside the editor. Built by Small Magellanic Cloud Ai Ltd, trading as SmallCloud AI, it plans a task, searches the repository for context, edits files, runs tests, and iterates until the work passes. It has ranked first among open-source agents on the SWE-bench Verified leaderboard, autonomously resolving 352 of 500 real GitHub issues, with the full benchmark pipeline published as open source so results can be reproduced.

The agent runs multi-step and is capped at thirty autonomous actions per task, breaking work into steps, proposing and applying patches, running self-tests and revisiting earlier steps when something fails.

A Rust engine runs inside the IDE as a language server, keeping abstract syntax tree and vector indexes of the codebase current and exposing symbol and semantic search as tools the model calls, alongside a debugging sub-agent that drives the Python debugger to modify and run scripts and isolate the cause of a failure.

Because developers want oversight, patches are proposed for review before they apply, the process can be previewed and guided step by step, and access can be scoped so the agent cannot touch protected files or projects.

Refact runs in VS Code, JetBrains, Visual Studio, Neovim and Sublime Text across 25+ languages, pairing the agent with code completion powered by a bundled Qwen2.5-Coder model and retrieval over the project. It integrates with GitHub and GitLab, PostgreSQL and MySQL databases, Docker, shell commands, the Python debugger, CI/CD pipelines, browser tools and MCP servers, so it can create a branch, implement an endpoint, run tests in a container, update a database and open a pull request from one prompt. Its browser tool drives Chrome, and in one customer account the agent operated a WordPress admin interface through Chrome to diagnose and fix a plugin fault.

Models are entirely the customer's choice. The agent runs on bring-your-own-key providers including OpenAI, Anthropic, Gemini, DeepSeek, OpenRouter, Groq and xAI, or on local runtimes including Ollama, LM Studio, vLLM and any OpenAI-compatible endpoint, configured on the developer's own machine.

In April 2026 Refact announced that Refact Cloud is shutting down. The managed cloud service, hosted accounts, Refact-issued model credits and the paid cloud subscription layer are all being retired. Active subscriptions will be terminated with recent invoices refunded, and there will be no paid hosted service or commercial support afterwards.

Refact has not published a final shutdown date, so the paid hosted tiers can still be bought, and its pricing still lists Free, Pro from $10/month and Enterprise alongside the shutdown notice. Refact itself continues as open source, local-first, BYOK and community maintained, with support and roadmap moving to GitHub issues, discussions and pull requests. The architecture had already moved local, so no hosted account is needed to keep using it.

Refact is open source under a permissive license and runs entirely self hosted, on premises or in a private cloud, with zero telemetry so code never leaves the customer's servers. It adds file and project level access restriction, audit logging for data access, and fine tuning on a team's own codebase. Refact names no security certification, SSO or organization level RBAC.

Vendor details

Canonical URL

https://refact.ai

Category

Coding agent

Subcategory

Open source autonomous coding agent (self hosted, BYOK)

Funding status

Independent, created by SmallCloud AI, with Refact distributed as open source under a permissive BSD-3-Clause license. Specific venture funding is not disclosed in available sources. The project reports being the number one open source AI agent on the SWE-bench Verified leaderboard. Note that the original open source repository is now maintained as a legacy archive, with active development continuing in a successor repository, while the IDE products and pricing remain live.

Company status

independent

Use cases & customers

Primary use cases

autonomous end to end task completion in the IDERAG powered code completion and refactoringself hosted private AI for regulated teamscodebase fine tuning to match team standardsbring your own model coding agent

Target customers

developers wanting an autonomous open source coding agentsecurity conscious and regulated enterprises needing self hostingteams that want to bring their own model keys

Deployment options

Open-source self-hosted (permissive license, on-premise or private cloud, zero telemetry)Local-first: local Refact engine running from the IDEIDE plugin (VS Code, JetBrains, Visual Studio, Neovim, Sublime Text)BYOK providers or local runtimes (Ollama, LM Studio, vLLM, custom OpenAI-compatible endpoints)

Integrations

Integrations span source control with GitHub and GitLab, relational databases with PostgreSQL and MySQL, Docker containers, shell commands, the Python debugger, browser tools, and MCP servers the agent consumes, alongside CI/CD pipelines. The agent connects to these resources and runs real operations autonomously, such as creating a branch, implementing an endpoint, running tests in a container, updating a database and opening a pull request from one prompt. It runs as a plugin in VS Code, JetBrains (PyCharm, WebStorm, GoLand, IntelliJ, CLion), Visual Studio, Neovim and Sublime Text, supporting 25+ languages. Models come from BYOK providers (OpenAI, Anthropic, Gemini, DeepSeek, OpenRouter, Groq, xAI) or local runtimes.

In practice

You want an autonomous agent that finishes tasks, not just autocomplete. Refact plans, edits, runs tests, and iterates until it passes, capped at thirty actions per task, and ranks first among open source agents on SWE-bench.

You cannot let code leave your servers. Refact is open source and runs fully self hosted on premises or in a private cloud with zero telemetry, file level access controls, and audit logs for data access.

You want to control model cost and choice. Refact lets you bring your own key for OpenAI, Anthropic, Gemini, or a local model, running the full agent with no Refact credits to buy, only your provider's charges.

Agentic Index coverage score

12.5 / 14 capabilities · 89%

Integrations & Tool Calling Full

Integrations span GitHub and GitLab for source control, PostgreSQL and MySQL databases, Docker containers, shell commands, the Python debugger, browser tools, and MCP servers the agent consumes, with CI/CD pipelines connected. The agent connects to a customer's GitHub, Docker and PostgreSQL to mimic developer behavior and complete tasks autonomously, such as creating a branch, implementing an endpoint, running tests in a container, updating a database and opening a pull request from a single prompt. Support covers 25+ programming languages.

Sourceplugins.jetbrains.com Refact listing, refact.ai and github.com/smallcloudairead 2026-08-30

Workflow Orchestration Full

The agent plans a task, searches and analyzes the repository for context, edits files, reproduces problems, runs tests and iterates until the work passes, executing up to thirty autonomous actions per task and revisiting earlier steps on failure, with internal sub-agents for planning and for debugging that drive the Python debugger to modify and run scripts; it carries a task from a single prompt through branch creation, implementation, containerized test runs and an opened pull request. Refact reports ranking first among open-source agents on SWE-bench Verified, autonomously resolving 352 of 500 real GitHub issues, with the benchmark pipeline published as open source.

Sourcegithub.com/smallcloudai, refact.ai and refact.ai/blog/2025/open-source-sota-on-swe-bench-verified-refact-airead 2026-08-30

Knowledge Grounding & RAG Full

A Rust engine runs inside the IDE as a language server and keeps abstract syntax tree and vector database indexes of the codebase current, exposing symbol and semantic search as tools the model calls, with retrieval-augmented generation grounding both agent work and completion in project context. Refact says the agent understands company context and standards by analyzing documentation and codebase, and enterprise deployments can fine-tune models on the organization's own code. Context sources named on the product page span workspace, codebase, databases, files, documentation and web.

Sourcegithub.com/smallcloudai and refact.airead 2026-08-30

Human Oversight & Guardrails Full

Tool execution is mediated by confirm rules in each mode's configuration: safe reads default to auto and destructive or sensitive operations to ask, and when a tool requires confirmation execution pauses until the user approves or rejects it; patch, create, update, remove, move and undo style operations require confirmation. Shell commands and integrations carry allow, ask and deny rules, and the agent is capped at thirty autonomous actions per task.

Sourcegithub.com/JegernOUTT/refact/wiki Agent-Tools, Integrations-Shell-Commands and Integrationsread 2026-09-29

Security, Identity & Governance Partial

Access can be restricted to particular files or projects so private or confidential code is withheld from the assistant, Refact says it never stores code server side and offers privacy settings, self hosted deployment runs on premise or in a private cloud with zero telemetry, and self hosted deployments keep audit logs for data access. With hosted Refact Cloud retired, there is no vendor side service retaining customer code. Refact does not describe a security attestation or certification, SSO, SAML or role based access control at the organization level.

Sourcedocs.refact.ai, refact.ai and refact.ai/blog/2026/refact-cloud-is-shutting-downread 2026-08-30

Observability & Auditability Partial

Each chat's trajectory, the chronological agent and chat history including tool execution, is persisted locally under .refact/trajectories and can be searched by the agent, reasoning is shown step by step in the editor, and proposed patches are inspectable before they apply; self hosted deployments keep audit logs for data access. These are local session records on the developer's machine, with no audit log of agent actions, telemetry export or run analytics for a team.

Sourcegithub.com/JegernOUTT/refact/wiki Chat-System and Memory-and-Knowledge, and refact.airead 2026-09-29

Memory & State Persistence Full

Durable project memory lives in the project scoped .refact/ directory: typed task memories (decision, spec, gotcha, risk, handoff, progress, postmortem, brief) preserve structured task knowledge across sessions for project scoped recall, and a knowledge graph of facts and relationships has staleness tracking and a cleanup pass that removes stale or duplicate nodes. The files sit in the project on disk. The VecDB and AST indexes are separate from this memory and ground the agent in the codebase.

Sourcegithub.com/JegernOUTT/refact/wiki Memory-and-Knowledge, reached through the docs.refact.ai redirectread 2026-09-29

Deployment & Data Residency Full

The product is open source under a permissive license and local-first by design, running from the IDE with a local Refact engine and whichever providers or local runtimes the customer configures, with no hosted account or managed inference service required; on-premise and private cloud deployment keep code on the customer's own servers with zero telemetry, and local runtimes including Ollama, LM Studio and vLLM are supported. Hosted Refact Cloud is being retired, and Refact says the project continues as open source, local first, BYOK and community maintained, with local configuration and project data remaining under the customer's control and requests sent only to configured providers and integrations.

Sourcerefact.ai/blog/2026/refact-cloud-is-shutting-down and refact.airead 2026-08-30

Prebuilt Agents, Templates & Packs Full

An extensions marketplace discovers and installs three kinds of item, skills, commands and subagents, from built-in embedded sources, built-in GitHub sources and user-added GitHub sources, with the source index bundled in the engine. The catalog includes ready subagents a customer can install.

Sourcegithub.com/JegernOUTT/refact/wiki Marketplace, reached through the docs.refact.ai redirectread 2026-09-29

Triggers & Channel Coverage Full

The engine's scheduler runs cron-style scheduled tasks that fire into the agent: durable jobs persist per project in .refact/scheduled_tasks.json and survive restarts, use 5-field cron expressions with jitter, catch up missed one-shot runs and expire recurring jobs after 30 days by default. Invocation otherwise spans VS Code, JetBrains, Visual Studio, Neovim and Sublime Text plugins, a standalone CLI and TUI, and an in-browser GUI served by the local daemon.

Sourcegithub.com/JegernOUTT/refact/wiki Scheduler-and-Cron and Home, reached through the docs.refact.ai redirectread 2026-09-29

Model Flexibility & Routing Full

The agent runs on bring-your-own-key or local model providers configured on the customer's own machine, with at least one provider required in Provider Setup before use; named BYOK providers are OpenAI, Anthropic, Gemini, DeepSeek, OpenRouter, Groq and xAI, and named local runtimes are Ollama, LM Studio, vLLM and custom OpenAI-compatible endpoints, with default models selectable per surface. Code completion ships on a bundled Qwen2.5-Coder model. With Refact issued model credits retired, BYOK or a local runtime is the only way to run the agent.

Sourceplugins.jetbrains.com Refact listing and refact.ai/blog/2026/refact-cloud-is-shutting-downread 2026-08-30

APIs, SDKs & MCP Extensibility Full

The local engine exposes a v1 HTTP API covering chat, code, tools, AST, retrieval, git, checkpoints, integrations, knowledge and voice, and the GUI and IDE plugins are thin clients of that daemon, so other programs can drive Refact the same way. The engine and plugins are open source, and MCP servers the customer configures extend the agent.

Sourcegithub.com/JegernOUTT/refact/wiki HTTP-API and Home, reached through the docs.refact.ai redirectread 2026-09-29

Testing, Debugging & Optimization Partial

The agent reproduces a reported problem, runs the codebase's existing tests to avoid regressions, and iterates when they fail, with a dedicated debugging sub-agent that drives the Python debugger to modify and run scripts and isolate the cause of a fault; a standalone AI Code Review tool analyzes code and proposes fixes.

Refact publishes SWE-bench Verified results with the full benchmark pipeline open sourced for reproducibility. Running the project's tests checks the agent's own output, SWE-bench is Refact's own evaluation, and Refact does not offer customers evals, regression testing or a way to debug agent behavior.

Sourcerefact.ai/blog/2025/open-source-sota-on-swe-bench-verified-refact-ai and refact.airead 2026-08-30

Browser & Computer Use Full

Refact includes a built-in Chrome tool: the agent launches Chrome or Chromium, connects to an existing DevTools endpoint or reuses a session for the chat, opens and switches tabs, navigates, inspects and interacts with pages, extracts data and collects screenshots, for debugging web apps and checking UI behavior. A customer account on Refact's homepage describes the agent operating a WordPress admin interface to fix a plugin fault.

Sourcegithub.com/JegernOUTT/refact/wiki Browser-Automation and refact.airead 2026-09-29

The Agentic Index coverage score grades every vendor Full, Partial or Not documented against the same 14 buyer facing capabilities, from public evidence only. Each capability links to how all vendors in the index score on it. How this evidence is graded

Pricing

Free for personal and hobby projects, with limited daily agent use and unlimited completions. Pro is from $10 a month with 40 agent requests a day, and Enterprise is by contact. Hosted Refact Cloud is being retired with no final date published, and the open source local engine with the customer's own keys is free.

A monthly subscription limited by daily agent requests. The free plan allows limited daily agent use with unlimited completions, and Pro at $10 a month allows 40 agent requests a day. Bringing your own model key runs the open source engine with no Refact charge, so only the model provider bills.

Free tier

Included quota

The free plan includes limited daily agent use, chat with 32k context, unlimited completions on Qwen2.5-Coder, a code aware vector database and bring your own key support. Pro adds 40 agent requests a day, chat with 64k context and more completion models from $10 a month. The open source edition can be self hosted at no license cost, and bringing your own model key runs the full agent with no Refact charge beyond the provider's. Enterprise adds on premises deployment, fine tuning, and custom terms.

What is public

Refact publishes three plans. Free has limited daily agent usage, 32k chat, unlimited completions on Qwen2.5-Coder and vector RAG. Pro, from $10 a month, has 40 agent requests a day, 64k chat and more completion models. Enterprise is by contact. Refact announced in April 2026 that the paid hosted Refact Cloud layer will end, with the final date to be published separately, and there is no separate pricing page.

Billing mechanics

Refact sells a free tier and a Pro subscription from $10 a month, limited by daily agent requests, for as long as hosted Refact Cloud lasts. Bringing your own key or a local runtime runs the open source engine with no Refact charge.

Cost watchouts

Pro caps agent use at 40 requests a day, so autonomous multi step tasks use up the allowance faster than simple prompts. Bringing your own model key removes the Refact charge but shifts spend to the provider, billed by usage. Self hosting is free, but the customer runs and pays for its own infrastructure and any external model calls.

Variable cost rationale

On hosted Refact Cloud, Pro is a flat $10 a month with 40 agent requests a day, and the free plan allows limited daily agent use. The daily request limit, not a meter, holds the hosted bill in place, and heavy autonomous use runs into it. The variable cost sits outside Refact. Bringing your own model key moves agent usage to the model provider, billed by usage, and self hosting the open source engine moves cost to infrastructure and model calls. Hosted Refact Cloud is being retired, with no final date published.

Additional watchouts

Pro caps agent use at 40 requests a day, so heavy autonomous use needs the customer's own keys or a local runtime, billed through the provider. Enterprise and self hosted deployments add infrastructure and model costs. The original open source repository is now a legacy archive.

Overage / add-ons

No overage rate is published beyond Pro's 40 agent requests a day. Bringing your own model key moves usage to the provider's bill instead.

Sales call required

No, self serve available

Free / trial

Free plan for personal and hobby projects, with limited daily agent use, 32k context chat, unlimited completions and a code aware vector database. The open source engine is free with your own keys or local models.

Lowest paid plan

Pro at $10 per month, with 40 agent requests a day

Commercial notes

Refact has a free tier, a paid plan from $10 a month and a self hosted path that is free apart from infrastructure and model calls. Pro limits agent use by daily requests, and setups that bring their own key pay only their provider.

Key ambiguities

How far 40 agent requests a day goes depends on how heavily the autonomous agent is used. Bring your own key removes the Refact charge but replaces it with provider usage billing. Enterprise pricing is not public.

Cancellation / refund

Self serve plans can be changed or canceled by the user, and the open source self hosted edition carries no subscription. Enterprise terms are arranged directly.

Support SLA / resale

Enterprise adds priority support and onboarding, with deployment on premises, as SaaS or on AWS.

Missing data

Enterprise pricing and the final shutdown date of the paid hosted tiers are not published.

Agentic Index verified 2026-10-25

Alternatives to Refact.ai

The closest documented capability profiles to Refact.ai among coding agents tracked by Agentic Index, ordered by similarity on the same 14 point evidence the rankings use. No vendor pays for placement.

  • Kilo Code13.0 / 14Fuller documented coverage on Security, Identity & Governance
  • Cognition13.5 / 14Fuller documented coverage on Security, Identity & Governance and Observability & Auditability
  • GitHub Copilot13.5 / 14Fuller documented coverage on Security, Identity & Governance and Observability & Auditability
  • Hermes Agent12.5 / 14Fuller documented coverage on Observability & Auditability
  • Kiro13.5 / 14Fuller documented coverage on Security, Identity & Governance and Observability & Auditability
  • Base4413.0 / 14Fuller documented coverage on Security, Identity & Governance and Observability & Auditability

Similarity is computed from each vendor's Agentic Index coverage score evidence, axis by axis, not from the totals. How this evidence is graded

Head to head

Contact us

Found a vendor we missed? Have feedback on the index? We'd love to hear from you.