KikoCis/elffuss-code
🧑💻 Elffuss Code — 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 — real Monaco (the VS Code editor), a file tree, tabs — 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.
⚠️ Open it full-screen (direct link) — 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 — genuine tool-calling, not autocomplete.
Why it's different
- Your code stays local. The folder is opened via the File System Access API — 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— 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 — 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/pythonexecution — downloaded from the main site.
How it's built
Write-ups on the full stack — model, runtime, agent harness, editor and filesystem access, all in one tab: <https://bitacora.utopiaia.com/#elffuss>
Context management — 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):
Long-term memory (200 questions, F1 from the benchmark's own repo, a real model answering, ~8 % of the context):
Retrieving well beats having everything: 28.09 vs 22.56 using 8 % of the tokens. Irrelevant context isn't neutral ballast — it distracts.
Two more things that were measured, not assumed: turning the heuristics on cost −3.02 F1, and removing IDF costs −3.25. 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) — and fusion keeps both.
References: BM25 (Robertson et al., TREC-3 1994) · IDF (Spärck Jones, 1972) · RRF (Cormack et al., SIGIR 2009) · MMR (Carbonell & Goldstein, SIGIR 1998) · attention sinks (Xiao et al., ICLR 2024) · 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
- 🌐 Full app: <https://code.elffuss.utopiaia.com>
- 💻 Source (Apache-2.0): <https://github.com/KikoCis/elffuss-code>
- ✳️ Elffuss Claw — an agentic OS in your browser: <https://claw.elffuss.utopiaia.com> · Space
- 🧬 Shared core: <https://github.com/KikoCis/elffuss>
- 🗣️ Elffuss Translator — speech-to-speech translation on your device: <https://translator.elffuss.utopiaia.com>
- 📝 Elffuss Copilot — live call notes that never leave your browser: <https://copilot.elffuss.utopiaia.com>
- 📰 All apps and the blog: <https://elffuss.utopiaia.com>