slotstream - large moe models on a smaller mac
About Slotstream
Runs mixture-of-experts models that do not fit in a Mac's memory by streaming the experts it needs from SSD, so a 105 GB model can run on a 48 GB machine. Apple Silicon only, built on MLX, and focused on one model family rather than being a general local-model runner. Treat the throughput and SSD-wear figures as the project's own measurements: they are published and detailed, and no independent verification exists yet. The project is weeks old and moving quickly. Sevra, listed as its homepage, is a future consumer app built on top of it rather than a paid tier of it.
Key Capabilities
Streams MoE experts from SSD so a model larger than RAM will run
Built on MLX for Apple Silicon rather than wrapping llama.cpp
Publishes detailed measurements rather than round numbers
Ships its own security documentation and changelog
Perfect for
Compare Slotstream
Community Buzz
Community Buzz
No recent posts yet
We are monitoring X for fresh discussions about Slotstream.
Similar Tools to Slotstream
Vibe Kanban
Open-source kanban board for orchestrating AI coding agents. Plan tasks as issues, run Claude Code, Codex, or Gemini CLI in isolated git worktrees, review diffs inline, and open pull requests from one local UI. The company behind it (bloop) shut down in April 2026, but the project lives on as community-maintained open source and local workspaces keep working.
Hermes Agent
Self-hosted autonomous agent from Nous Research with a built-in learning loop. Creates skills from experience, persists memory across sessions, and runs 24/7 on your own hardware with sandboxed terminals and messaging-app gateways.
Moadim
A loop engine that runs coding agents on a schedule against your codebase. A loop pairs a prompt, a schedule and an agent (Claude, Codex, Hermes, NanoClaw or Pi), and each run executes in a throwaway workbench so a hung run gets killed rather than left behind. Everything is exposed twice, as a REST endpoint and as an MCP tool, so another agent can schedule work as easily as you can. Routines live in ~/.config/moadim/ and are git-trackable. It runs entirely on your own machine: no cloud, no account, no data leaving the host.
OKF Agent Memory
Persistent memory for coding agents kept as plain files in your repository rather than in a vector database. It implements Google's OKF v0.2 specification with progressive disclosure, so the agent pulls in only the slice of memory a task needs instead of paying for the whole store on every request, and retrieval uses BM25 rather than embeddings. Because the memory is git-native it diffs, reviews and reverts like the rest of your code, and it publishes its own security documentation, which is unusual for a tool whose entire job is persisting context to disk.
Orca
Open-source Agent Development Environment for running a fleet of AI coding agents at once. Every task gets its own git worktree, its own agent terminal, and its own browser tab, so you can fan one prompt across several agents, compare the diffs, and merge the winner. It drives roughly 30 CLI agents you already pay for, including Claude Code, Codex, OpenCode, Cursor and Copilot, and ships on macOS, Windows, Linux, iOS and Android.
Parallel Code
Free, open-source desktop app that dispatches AI coding agents in parallel, each in its own git worktree. It runs the real CLI agents you already trust (Claude Code, Codex, Gemini) side by side, then lets you review the diffs, merge the wins, and toss the rest.
Browse vetted vibe coding agencies for MVP builds, cleanups, and audits.
ready to try slotstream?
go to the official site and judge Slotstream yourself.
try slotstream now