Refact.ai
An open-source AI coding agent with chat and autocomplete, and a self-hosted option.
- Starting price
- Free tier; Pro $10 / month
- Free trial
- Free tier
- Commercial use
- Yes
Overview
Refact.ai is an open-source AI coding agent that combines an autonomous agent, in-IDE chat and real-time code completion in one tool. The agent plans and executes end-to-end coding tasks, completion runs on a Qwen2.5-Coder model with retrieval for project context, and chat carries 32k tokens of context on the free plan and 64k on Pro. It works across VS Code and the JetBrains family, and supports models from Anthropic and OpenAI alongside bring-your-own-key access. A self-hosted version keeps code under the team's control.
Our take
Refact bundles three things developers usually buy separately into one open-source plugin, and it can run on-premise, which is the reason most teams look at it rather than at a hosted assistant. If nothing in your work forbids sending source to a vendor, the on-premise option stops being the reason to pick it, and a hosted commercial assistant is the alternative at the same money. The free plan's daily agent limit is the thing to test against a real week, because that, and not the chat context, is where regular use runs out.
Key Facts
| Category | |
|---|---|
| Starting price | Free tier; Pro $10 / month The free plan includes unlimited completions and limited daily agent use. Enterprise is custom, with on-premise deployment and fine-tuning. |
| Free trial | Free tier |
| Commercial use | Yes |
| Output | Agentic coding, chat and completion in the IDE |
| API | Bring your own key |
| Hosting | Cloud or self-hosted on-premise |
Screenshots
Placeholders. They are replaced as soon as the vendor sends material, and both open the same short form.
Features
- Where it runs
- Plugins for VS Code and JetBrains IDEs, with Visual Studio, Neovim and Sublime Text in beta
- Inline completions
- Yes, real-time completion on Qwen2.5-Coder with retrieval for context
- Agent mode
- Yes, an autonomous agent that plans and executes multi-step tasks
- Model choice
- Claude and GPT models built in, plus bring-your-own-key for Gemini, Grok and DeepSeek
- Data control
- Self-hosted, on-premise deployment keeps code private
- Ecosystem fit
- IDE plugins across VS Code and JetBrains, open source with a self-hosted server
- API
- Bring your own key
Integrations
Integrations coming soon.
Deployment and Support
- Deployment
-
- Cloud (SaaS)
- On-premise
- Onboarding
-
- Documentation and knowledge base
- Company size
-
- Freelancers
- Small and mid-sized
- Enterprise
Suitability
| Industry | Freelancers | Small and mid-sized | Enterprise |
|---|---|---|---|
| Agencies | Not stated | Not stated | Not stated |
| Architecture & Engineering | Not stated | Not stated | Not stated |
| Consulting | Not stated | Not stated | Not stated |
| Media & Creative | Not stated | Not stated | Not stated |
| Technology | Stated as a fit | Stated as a fit | Stated as a fit |
The table combines the industries the vendor addresses with the company sizes the tool is aimed at. An empty cell means the combination is not stated, not that it is ruled out.
Pros and Cons
Strengths
- Open source with a self-hosted, on-premise option
- Agent, chat and completion in one plugin
- Broad model choice through bring-your-own-key
Limitations
- Free plan caps daily agent runs
- Some IDE plugins are still in beta
Pricing
-
Free
$0
Unlimited completions, limited daily agent use, 32k context chat.
-
Pro
$10
Per month. 40 agent requests per day, 64k context chat.
-
Enterprise
Not stated
Custom. On-premise deployment and fine-tuning.
Best For
Alternatives and Comparisons
What users say
Reviews
-
0 reviews
- Ease of use
- Not rated yet
- User interface
- Not rated yet
- Onboarding
- Not rated yet
- Support and service
- Not rated yet
- Value for money
- Not rated yet
- Features
- Not rated yet
No reviews yet. Nothing has been published here yet, and no score is shown. How a review is checked before it appears is described below.
How we check reviews
Reviews are not published yet. The form on a tool's page works and reaches us, but nothing from it appears on this site, so no score here is based on a review. The rules below are the ones that will apply once reviews go live.
Every review is read by a person before it appears. We require a working email address and use it to come back to the author, so a review has a reachable sender rather than being anonymous. We publish positive and negative reviews alike, we pay nothing and offer nothing for a review, and we accept none that was bought or incentivised.
What we cannot do is verify a purchase. There is no shop here and no account, so whether the author really used the tool rests on what they tell us, plus the plausibility of what they write. We say so rather than implying a check that does not exist.
A vendor cannot have a review removed, cannot buy one, and cannot have one changed. Paid placement and a paid listing have no effect on which reviews appear or on any score.
Share your experience
Write a Review
Ready to take a closer look at Refact.ai
The link goes straight to the vendor. Some links on this site are affiliate links.
Visit Refact.ai