refact

You realize that you can self-host their stuff? https://github.com/smallcloudai/refact

Open-source Refact.ai achieves #1 on SWE-bench Lite with a 59.7% score. Our approach: fully autonomous Agent, no manual intervention needed. How we did this: • Prompt strategy: https://github.com/smallcloudai/refact/blob/swe-boosted-prom... • Claude 3.7 Sonnet as orchestrator • deep_analysis() tool (powered by o4-mini) for reasoning • Tool suite for repository exploration, code modification, and testing. Used dynamically based on task needs • One correct solution through iteration! Autonomy = our core strength. Refact.ai Agent completes the entire dev workflow independently: plans, executes, tests, self-corrects, and delivers a production-ready result. For each task, it made one multi-step run to generate a single correct solution, creating custom strategies rather than following rigid scripts. You can read tech details on our SWE-bench

You should check-out https://github.com/smallcloudai/refact. It has both autocomplete and chat. It's in active development, with lots of new features coming soon (context search, fine-tuning for larger models, etc)

That is not what I consider "local", since that uses cloud inference by default (and last I checked, they provided no useful guidance for changing that). I don’t consider cloud inference to count as getting it working “locally” as requested by the comment above yours. Refact worked nicely and worked locally when I tried it a few weeks ago, but the challenge with any new model is making it be supported by the existing software: https://github.com/smallcloudai/refact/

We’ve finished training a new code model Refact LLM which took us about a month. The main use-case is for blazing-fast code completion with fill-in-the-middle, additionally, the model could reply to chat prompts. It has much better performance than all of the code models of similar size, and almost reaches the same HumanEval as Starcoder being 10x smaller in size. With the small size, it can work with most modern GPUs requiring just 3GB Ram. You can try self-hosting it in Refact https://github.com/smallcloudai/refact/ and get a local fast copilot alternative with decent suggestions. Weights and model card https://huggingface.co/smallcloudai/Refact-1_6B-fim. We would love to hear your feedback!

at Refact we have Jetbrains plugin that works with a bunch of local code models https://github.com/smallcloudai/refact/

we're going in this direction for code models with Refact https://github.com/smallcloudai/refact/ - right now you self-host code models, fine-tune them on local files, get the model running locally inside your IDE

try refact.ai they have plugin for JetBrains IDEs and support for local LLMs https://github.com/smallcloudai/refact/

there's also Refact (https://github.com/smallcloudai/refact/) with support of several open-source code LLMs and extension for VS Code and Jetbrains

I have been using refact.ai on my laptop, it has been quite good. https://github.com/smallcloudai/refact/blob/main/README.md

For in-editor like copilot you can try this locally - https://github.com/smallcloudai/refact This works well for me except the 15B+ don't run fast enough on a 4090 - hopefully exllama supports non-llama models, or maybe it'll support CodeLLaMa already I'm not sure. For general chat testing/usage this works pretty well with lots of options - https://github.com/oobabooga/text-generation-webui/