Early access. The mesh is live and under active development — latency and uptime vary. Paid API preview · Earner dashboard · Settlement books · Contributor credits (not cash); Peer USD may accrue on paid serves. Free chat stays free. Security →
Senda
Open peer-to-peer LLM mesh.
Run a node
Contribute compute

Run a node. Serve the mesh. Track contribution.

Senda routes chat and API traffic to peers whose hardware fits each model. Contributors who serve real sessions accumulate contributor credits — a measure of contribution, tracked in the app. Paid /v1 mesh serves may also accrue a separate peer USD liability (bind wallet in desktop for self-serve). Check both on /earn with Phantom. Separate from the customer API balance on /buy.

Reading the mesh…
Download desktop appInstall CLI runtimeLive status →
Peer clusters linked by curved luminous routing lines
Peer clusters linked by curved luminous routing lines

How credits work (early access)

The runtime counts completion tokens your machine serves to mesh requests over a rolling 7-day window, then weights each token by how hard its model is to serve. That weighted count is your credits — measured in tokens, not dollars. We don't price a token in cash, so we don't pretend to.

Daily driver
×1 credits / token served

8B–14B class models at chat-viable latency. Highest volume, most contributors.

Example: 5.0M tokens served → 5,000,000 credits

Capacity
×5 credits / token served

32B–70B models that fit on beefy solo peers or pooled splits. Scarcer capacity, so each served token is weighted heavier.

Example: 0.5M tokens served → 2,500,000 credits

Credits are a measure of contribution — not a payout. They accrue on the public ledger when your peer serves mesh traffic, attributed to the serving host and weighted by model tier. Separately, paid /v1 mesh serves may accrue Peer USD — bind a Solana wallet in the desktop app and withdraw USDC once you clear the minimum (preview, capped, kill-switchable). History on /earn; public settlement books on /metrics.
Loading credits leaderboard…
Check your credits

Find your node id on /status and paste it to see your accrued early-access credits.

Why run a node?

  • Turn idle hardware into mesh capacity. An M-series Mac with 16GB+ unified memory or a CUDA box with 12GB+ VRAM can serve daily-driver models while you sleep.
  • See contribution in the dashboard. Tokens served, models loaded, uptime, and estimated credits appear in the desktop app's local controller.
  • Open runtime you can audit. Same stack whether you contribute or run entirely for yourself. Read the threat model before sharing a machine you care about.

Hardware that works well

PlatformBackendSweet spot
Apple Silicon MacMetalQwen3-8B solo; 30B+ with enough unified memory
Linux / Windows NVIDIACUDADaily-driver + capacity models on 12GB+ VRAM
AMD / Intel GPUVulkan / ROCmDaily-driver tier; join the mesh, measure on /status

The installer at senda.network/install detects your platform and pulls the matching runtime build.

Get started in three steps

  1. 1
    Install

    Download the desktop app or run the install script. The runtime autostarts and joins the public mesh via an embedded invite token.

  2. 2
    Share a model

    Pick a model your hardware fits — start with Qwen3-8B-Q4_K_M if unsure. The dashboard shows load progress and when you're serving.

  3. 3
    Watch credits accrue

    Serve mesh chat or API traffic. The dashboard's contribution card updates from real completion-token counts. Check /status to see yourself on the public catalog.

Questions or want to join the first operator cohort? Open a discussion on GitHub Discussions. Ship log: /updates.