edge0-ai / edge0 Architecture and code health
Run 35B MoE models in ~2.5 GB of RAM. Weights stream from SSD; a trained router predicts loads a step ahead. Mac, iPhone, Android, Windows supported
github.com/edge0-ai/edge0Indexed at d4a2fa0Up to date with upstream
About this codebase
edge0 is a streaming MoE inference engine: it takes a sparse mixture-of-experts checkpoint, its trained Recover-LoRA adapters and prerouter heads, streams expert weights from SSD on demand, and produces generated text through a local HTTP API and native chat applications, so large models run on consumer hardware with peak memory bounded by the active expert set rather than the parameter count.
Written by a model from the index
819 files and 11,054 symbols in 5 modules, led by C++ (419 files) and Python (80).
Code health
Hotspots average 6.0, the place fixes pay off most.
On the leaderboards:#30 of 57 Python repos
Use edge0-ai/edge0 in your agent
Point Claude Code, Cursor, Codex or VS Code at this repository. Your agent gets the index this page is built from: cited answers, callers, history and health for any file.
- 1.In Claude, open Customize → Connectors, click +, then Add custom connector. On a Team or Enterprise plan an owner adds it first under Organization settings → Connectors.
- 2.Paste the server URL below as the Remote MCP server URL, then click Add.
- 3.Click Connect. A Repowise sign-in window opens. Approve access.
- 4.Repowise's tools are now available in your Claude chats.
Connect with one click. Sign in with Repowise (OAuth), no API key to copy. Works in Claude on the web, desktop, and mobile.
Docshttps://api.repowise.dev/mcp/edge0-ai/edge0
This repo is public, so anyone with a Repowise account and an API key can connect.
Try asking
- get_risk(["python/src/edge0/server/app.py"])
- get_answer("how is edge0 put together?")
- get_why("why is edge0 structured this way?")
Explore edge0
- DocumentationModule-by-module documentation, 1,378 pages.
- ArchitectureDependency graph, layers and third-party dependencies.
- Code healthEvery file's score and the findings behind it.
- CommitsEach commit's effect on code health.
- OverviewEverything else the index found: contributors, decisions, what changed this week.
How edge0-ai/edge0 works
The codebase has 819 files and 11,054 symbols in 5 modules, led by C++, Python and TypeScript. Code health is 6.8 out of 10, rated fair.
About this page
Get a page like this for your own codebase
Repowise built this map of edge0-ai/edge0 from its source and git history. It parses every symbol, draws the dependency graph, scores each file's health from complexity, duplication, coverage and churn, finds hotspots and owners in the history, and writes documentation for every module. Your coding agent reads the same index over MCP, so its answers cite real files.
Prefer local? pip install repowise && repowise init indexes your own checkout, no account needed.
Maintain edge0-ai/edge0?
Claim this page, add a badge to the README, or re-index it.
Claim this page
Sign in with GitHub and we check that you are an admin or maintainer of edge0-ai/edge0. Then add a badge to the README that links readers here.
Add a badge to your README
Every badge is public, cached, and updates on its own after every index. Nothing to install.
Repowise badge
Links to this page, with no score on it. Adding it also re-indexes the repo every week.
[](https://repowise.dev/repo/edge0-ai/edge0?src=badge_wiki)Code health badge
The repo's health score out of 10, from the latest index.
[](https://repowise.dev/repo/edge0-ai/edge0?src=badge_health)Code health card
A larger card with the score, its change since the last index, and when it was measured. The HTML version follows the reader's light or dark theme.
[](https://repowise.dev/repo/edge0-ai/edge0?src=badge_card)