Refact.ai
As of our capture of refact.ai on 1 August 2026, the homepage carries a banner stating that Refact Cloud - the hosted service - is shutting down soon; the open-source, self-hosted build is not said on that page to be affected, and the pricing and hosted-tier facts below should be read with that in mind. Refact.ai is a coding agent that runs inside the developer's IDE, working against their codebase and stack; the vendor says it plans, executes and deploys from a described task, completing work step by step with reasoning the user can preview and control. It is powered by the Qwen2.5-Coder model with retrieval-augmented generation, and customers can use Claude 4, GPT-4o or GPT-4o mini, or connect their own API key to run Gemini, Grok, OpenAI or Deepseek models, and fine-tune on their own stack. Plugins are published for VS Code, JetBrains IDEs (PyCharm, WebStorm, GoLand, IntelliJ, CLion), Visual Studio, Neovim and Sublime Text, several marked beta. The Pro tier starts at $10 per month, and on-premise deployment is offered as the data-control option. The homepage headline calls the product open source but names no licence on the page checked. Beyond that, Refact.ai publishes little a buyer could rely on: no certification, no regulatory posture, no retained record of agent actions, no AI liability cover or indemnity, and no outcome-linked payment term. It scores 0 on four of the five trust-gap dimensions and 1 on the fifth.
18 fields evidenced · 37 with no public information. Every value below links to the document it came from and the date we checked it.
12 of those are quoted but not yet interpreted: we hold the source sentence and the date we read it, but nobody has written the answer to the question yet. Those rows show the quote and say so rather than repeating it back as an answer. Why these exist
4 of those are flagged for review: our own check found language in the cited source that may address the field. An editor has not adjudicated them yet.
Also appears in
Trust gap
How this is scoredAre scope, spend, and authority enforced while the agent runs?
The only governance claim is that the agent works "like another developer in your IDE... while letting you preview and control the process" — an unspecified preview and control affordance. No enforced limit on scope, spend or authority is published, and no permission scoping is described.
Counts Human oversight, each cited below.
How this gap gets closed →Is there a tamper-evident record of what it actually did?
No public evidence found. The page checked describes step-by-step reasoning shown to the user during a task but publishes no retained, reviewable record of agent actions, no log retention and no tamper-evidence claim.
Counts Explainability, each cited below.
How this gap gets closed →Are compliance obligations attached per engagement?
No public evidence found. The page checked names no certification, attestation or regulatory posture. Its only related claim is that on-premise deployment keeps code under the customer's control, which is a deployment option rather than a compliance position.
Counts Data handling, each cited below.
How this gap gets closed →Does payment depend on a verified result?
Payment is decoupled from result: the published Pro tier is a flat subscription "From $10/month — for professional use." No escrow, milestone release, clawback or outcome-linked term is published.
Counts Price point, each cited below.
How this gap gets closed →Can the deployment be insured, and is the customer indemnified?
No public evidence found. The page checked publishes no AI liability cover for a customer deploying Refact.ai, no named carrier, no policy limits, no customer indemnity and no liability cap.
How this gap gets closed →Assurance
- Insurance available
- no public informationrefact.ai · checked Aug 1, 2026 · source did not state this
- Insurance carriers
- no public informationrefact.ai · checked Aug 1, 2026 · source did not state this
- Coverage limits
- no public informationrefact.ai · checked Aug 1, 2026 · source did not state this
- Indemnification
- no public informationrefact.ai · checked Aug 1, 2026 · source did not state this
- Liability cap
- no public informationrefact.ai · checked Aug 1, 2026 · source did not state this
- Audit trail
- no public informationrefact.ai · checked Aug 1, 2026 · source did not state this
- Tamper-evident log
- no public informationrefact.ai · checked Aug 1, 2026 · source did not state this
- Explainability
“Completes task step-by-step with reasoning.”
refact.ai · checked Aug 1, 2026- Runtime governance
- no public informationrefact.ai · checked Aug 1, 2026 · source did not state this
- Permission scopes
- no public informationrefact.ai · checked Aug 1, 2026 · source did not state this
- Compliance certifications
- no public informationrefact.ai · checked Aug 1, 2026 · source did not state this
- Regulatory alignment
- no public informationrefact.ai · checked Aug 1, 2026 · source did not state this
- Outcome-based pricing
- no public informationrefact.ai · checked Aug 1, 2026 · source did not state this
- Settlement mechanism
- no public informationrefact.ai · checked Aug 1, 2026 · source did not state this
- Dispute process
- no public informationrefact.ai · checked Aug 1, 2026 · source did not state this
- SLA terms
- no public informationrefact.ai · checked Aug 1, 2026 · source did not state this
- Evaluation coverage
- no public informationrefact.ai · checked Aug 1, 2026 · source did not state this
Agency
- Autonomy level
“Autonomous AI agent Delegate your coding tasks end-to-end Just describe what you need — Refact.ai Agent plans, executes, and deploys.”
refact.ai · checked Aug 1, 2026- Human oversight
“It works like another developer in your IDE, integrating with your codebase and stack, while letting you preview and control the process.”
refact.ai · checked Aug 1, 2026- Goal complexity
“Completes task step-by-step with reasoning.”
refact.ai · checked Aug 1, 2026- Action space
“Refact.ai Agent accesses your resources and handles related operations autonomously, mimicking your workflow.”
refact.ai · checked Aug 1, 2026- Operating environment
- Runs inside the developer's IDE, working against their codebase and stack
“It works like another developer in your IDE, integrating with your codebase and stack, while letting you preview and control the process.”
refact.ai · checked Aug 1, 2026 - Initiative
- no public informationrefact.ai · checked Aug 1, 2026 · source did not state this
Safety
- Safety evaluations
- no public informationrefact.ai · checked Aug 1, 2026 · source did not state this
- Red teaming
- no public informationrefact.ai · checked Aug 1, 2026 · source did not state this
- Safety policy
- no public informationrefact.ai · checked Aug 1, 2026 · source did not state this
- Usage restrictions
- no public informationrefact.ai · checked Aug 1, 2026 · source did not state this
- Model or system card
- no public informationrefact.ai · checked Aug 1, 2026 · source did not state this
- Incident reporting
- no public informationrefact.ai · checked Aug 1, 2026 · source did not state this
- Third-party evaluations
- no public informationrefact.ai · checked Aug 1, 2026 · source did not state this
- Data handling
- On-premise deployment offered as the data-control option; no retention, training-use or deletion terms published on the page checked
“On-premise deployment keeps your code private and fully under your control. It provides maximum security and complete data ownership.”
refact.ai · checked Aug 1, 2026
Practicality
- Pricing model
- no public informationrefact.ai · checked Aug 1, 2026 · source did not state this
- Price point
“Pro From $10/month — for professional use”
refact.ai · checked Aug 1, 2026- Availability
- Hosted service being discontinued - the homepage carries a banner stating Refact Cloud is shutting down soon
“Refact Cloud is shutting down soon”
refact.ai · checked Aug 1, 2026 - Deployment options
- no public information
Flagged for review — the source below contains language that may address this field. Not yet checked by an editor. How we check absences
refact.ai · checked Aug 1, 2026 - Integrations
- no public information
Flagged for review — the source below contains language that may address this field. Not yet checked by an editor. How we check absences
refact.ai · checked Aug 1, 2026 - Supported regions
- no public informationrefact.ai · checked Aug 1, 2026 · source did not state this
- Support model
- "Priority support and onboarding" named as a paid-tier feature; no response times or remedies published
“Priority support and onboarding”
refact.ai · checked Aug 1, 2026
Foundation models
- Base models
“Powered by Qwen2.5-Coder model and Retrieval-augmented generation (RAG)”
refact.ai · checked Aug 1, 2026- Model provider
“Use Claude 4, GPT-4o, or GPT-4o mini with AI Agent or for chat queries. Bring your own key Connect your API key and use any LLM: Gemini, Grok, OpenAI, Deepseek, and others.”
refact.ai · checked Aug 1, 2026- Model swappable
“Bring your own key Connect your API key and use any LLM: Gemini, Grok, OpenAI, Deepseek, and others.”
refact.ai · checked Aug 1, 2026- Open weights
- no public informationrefact.ai · checked Aug 1, 2026 · source did not state this
- Fine-tuning
“Fine-tune LLMs Train AI on your stack to customize its behavior.”
refact.ai · checked Aug 1, 2026- Context window
- no public information
Flagged for review — the source below contains language that may address this field. Not yet checked by an editor. How we check absences
refact.ai · checked Aug 1, 2026
Ecosystem
- Protocols supported
- no public informationrefact.ai · checked Aug 1, 2026 · source did not state this
- Tool use
“Refact.ai Agent accesses your resources and handles related operations autonomously, mimicking your workflow.”
refact.ai · checked Aug 1, 2026- Multi-agent
- no public informationrefact.ai · checked Aug 1, 2026 · source did not state this
- API access
- no public information
Flagged for review — the source below contains language that may address this field. Not yet checked by an editor. How we check absences
refact.ai · checked Aug 1, 2026 - Open source
- Self-described as open source in the homepage headline; no licence named on the page checked
“Your Open-Source, Autonomous AI Agent”
refact.ai · checked Aug 1, 2026 - Marketplace presence
- Plugins published for VS Code, JetBrains IDEs (PyCharm, WebStorm, GoLand, IntelliJ, CLion), Visual Studio, Neovim and Sublime Text; several marked beta
“Download Refact.ai plugins: VS Code JetBrains Visual Studio beta Neovim beta Sublime Text beta PyCharm WebStorm GoLand IntelliJ CLion”
refact.ai · checked Aug 1, 2026
Impact
- User base
“Code agent trusted by thousands of developers”
refact.ai · checked Aug 1, 2026- Deployment scale
- no public informationrefact.ai · checked Aug 1, 2026 · source did not state this
- Target sectors
- no public informationrefact.ai · checked Aug 1, 2026 · source did not state this
- High-risk domains
- no public informationrefact.ai · checked Aug 1, 2026 · source did not state this
- Documented incidents
- no public informationrefact.ai · checked Aug 1, 2026 · source did not state this
Compared with
Side-by-side on the fields where Refact.ai and the other entry are both on record and actually differ.