Spaces:
Running
Running
|
Download README.md from UtopiaIA/elffuss-code: direct link, hf CLI and curl.
- Browser
- Download file 4.59 kB
-
https://huggingface.co/spaces/UtopiaIA/elffuss-code/resolve/main/README.md
- Command line
-
hf download hf://spaces/UtopiaIA/elffuss-code/README.md
-
curl -L -o README.md https://huggingface.co/spaces/UtopiaIA/elffuss-code/resolve/main/README.md
4.59 kB
| title: Elffuss Code | |
| emoji: π§βπ» | |
| colorFrom: purple | |
| colorTo: pink | |
| sdk: static | |
| app_file: index.html | |
| pinned: false | |
| license: apache-2.0 | |
| short_description: A VS Code-style IDE with a local AI agent, in-browser | |
| tags: | |
| - webgpu | |
| - transformers.js | |
| - local-llm | |
| - agent | |
| - code | |
| - gemma | |
| # π§βπ» Elffuss Code β a VS Code-style IDE with an AI agent, 100% in your browser | |
| Open a local folder and a full web IDE unfolds around it β real Monaco (the VS Code editor), | |
| a file tree, tabs β with an AI agent that **reads, searches and edits your project for real**. | |
| The model runs on **your** GPU via WebGPU. Your code never leaves your machine. | |
| > β οΈ **Open it full-screen** ([direct link](https://kikocis-elffuss-code.static.hf.space)) β the | |
| > File System Access API (opening a local folder) is blocked inside the embedded iframe. | |
|  | |
| In the demo a **small model running entirely in the browser** reads `calc.py`, finds a real | |
| bug and fixes it with a minimal edit β genuine tool-calling, not autocomplete. | |
| ## Why it's different | |
| - **Your code stays local.** The folder is opened via the File System Access API β no upload, no account. | |
| - **The model runs on your GPU** (WebGPU, Gemma-4 E4B via LiteRT-LM; ONNX/transformers.js as fallback). | |
| - **Real tool-calling**: `code.tree`, `code.read`, `code.search`, `code.edit`, `code.write` β you watch every call. | |
| - **Edits, not rewrites**: the agent patches the lines that change, even in files of several megabytes. | |
| - **Long tool results don't break the conversation**: they are compacted to fit the model's context instead. | |
| - **Context retrieval that works beyond English** β accents and Cyrillic included (measurements below). | |
| - **Real editor**: Monaco, file tree, tabs, `Ctrl+S`, and git branch/last commit parsed straight from `.git`. | |
| - **Zero install, zero build.** Vanilla ES modules. | |
| - **Your language**: the whole IDE follows your browser's language (English, Spanish and more). | |
| - External providers (OpenAI, Anthropic, Ollama) are **opt-in**; keys stay in your browser. | |
| - Optional local **bridge** for real `node` / `npm` / `python` execution β downloaded from the main site. | |
| ## How it's built | |
| Write-ups on the full stack β model, runtime, agent harness, editor and filesystem access, | |
| all in one tab: **<https://bitacora.utopiaia.com/#elffuss>** | |
| ## Context management β how it's measured | |
| The context packer isn't chosen by intuition. Numbers measured at the **same token budget**: | |
| **Real agent sessions** (25 sessions, 174 probes, fact recall, no LLM judge): | |
| | | recall | | |
| |---|---| | |
| | tail truncation | 7.0 % | | |
| | previous version | 15.1 % | | |
| | **current** | **65.3 % Β± 8.5** | | |
| **Long-term memory** (200 questions, F1 from the benchmark's own repo, a real model answering, ~8 % of the context): | |
| | | F1 | | |
| |---|---| | |
| | **the FULL context, uncompressed** | **22.56** | | |
| | tail truncation | 6.62 | | |
| | hand-written heuristics | 6.07 | | |
| | BM25 without IDF | 20.34 | | |
| | BM25 | 23.59 | | |
| | embeddings | 23.95 | | |
| | **rank fusion (BM25 + embeddings)** | **28.09** | | |
| **Retrieving well beats having everything**: 28.09 vs 22.56 using 8 % of the tokens. Irrelevant context | |
| isn't neutral ballast β it distracts. | |
| Two more things that were measured, not assumed: turning the heuristics on cost **β3.02 F1**, and | |
| removing IDF costs **β3.25**. Semantic search doesn't replace lexical search, it covers its blind spot: | |
| with no vocabulary overlap between question and answer, embeddings win (24.28 vs 18.60); with overlap, | |
| BM25 wins (29.33 vs 23.58) β and fusion keeps both. | |
| References: BM25 (Robertson et al., TREC-3 1994) Β· IDF (SpΓ€rck Jones, 1972) Β· RRF (Cormack et al., SIGIR 2009) Β· | |
| MMR (Carbonell & Goldstein, SIGIR 1998) Β· attention sinks (Xiao et al., ICLR 2024) Β· valid time (Snodgrass & Ahn, SIGMOD 1985). | |
| The full story, including what went wrong: <https://bitacora.utopiaia.com/posts/16-beaten-by-doing-nothing.html> | |
| ## The Elffuss family | |
| - π Full app: <https://code.elffuss.com> | |
| - π» Source (Apache-2.0): <https://github.com/KikoCis/elffuss-code> | |
| - β³οΈ Elffuss Claw β an agentic OS in your browser: <https://claw.elffuss.com> Β· [Space](https://huggingface.co/spaces/KikoCis/elffuss-claw) | |
| - 𧬠Shared core: <https://github.com/KikoCis/elffuss> | |
| - π£οΈ Elffuss Translator β speech-to-speech translation on your device: <https://translator.elffuss.com> | |
| - π Elffuss Copilot β live call notes that never leave your browser: <https://copilot.elffuss.com> | |
| - π° All apps and the blog: <https://elffuss.com> | |