Prototype · Preview: every server in the official registry, synced every 30 minutes. Sign in with Google to write reviews.Prototype · updated every 30 min
PopNx MCPMCP servers for people who use AI · explained in plain words Sign in

Nightshift Grid

by redd34version 0.1.3i★ 1iRuns on your computerRepository ↗
Registry nameio.github.redd34/nightshift-grid

How to install

What it does

Cited knowledge graphs from local documents, extracted by small Ollama models on idle machines.

  • Connects Runs on your computer
  • Account or key No key needed
  • Category Docs, sheets & office work

Use together with

Skills that teach the AI this kind of work; they work alongside this one

MinerU

Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.

by opendatalab★ 83,9721 skills

Skill · How-to guideNo license stated

watermarks-remover

A privacy-first app that strips AI watermarks from content you own.

by guillaumemeyer★ 27,7961 skills

Skill · How-to guide

obsidian-skills

Agent skills for Obsidian. Teach your agent to use Obsidian CLI and open formats including Markdown, Bases, JSON Canvas.

by kepano★ 53,242 (whole repo)5 skills

Skill · How-to guide

Why it ranks here

Lists are ordered by a usage score (out of 100) built from these parts

Popularity4/80GitHub stars or weekly downloads: the larger counts 60, the smaller 20
Freshness12/12Full marks for a release or code change within 30 days
Still answering0/8The cloud endpoint answered at the last check
Usage score16/100

Quality: Passed 3/3 basic checks (shown, not used for ordering) · Momentum: No data yet (Used only on the Trending tab)

Install

Pick the AI app you use, then copy the settings.

Let your AI install it with one sentence

Please install Nightshift Grid. Follow https://mcp.popnx.com/i/redd34-nightshift-grid.md, show me the commands and wait for my OK before running them.

Paste it into an AI that can work on your computer (such as Claude Code or Cursor). It reads our steps, shows you the commands and waits for your OK. No key, no sign-up. · See the full text your AI reads

Passed 3/3 checks · Runs on your computer · ✓ Commands checked Nov 15, 2026

First: which AI do you use?

Pick your app and the steps appear below.

Works with Claude, with some setup first

Install Python (uv) on your computer first (one time) · Only the Claude desktop app (Windows or Mac), not the web or phone

Let AI install it

Copy this message into a Claude chat. The AI checks your computer, tells you which file it will change, and waits for your OK every time.

Please install the MCP server Nightshift Grid for Claude on this computer, in this order: 1) Check uv with uv --version. If it is missing, tell me to install it from https://docs.astral.sh/uv/getting-started/installation/; do not install it yourself. 2) Use only this config (already checked by PopNx MCP): { "mcpServers": { "nightshift-grid": { "command": "uvx", "args": [ "nightshift-grid" ] } } } 3) Tell me the full path of the file you will change, or the command you will run, and wait for my OK. 4) No key is needed. 5) Do what we agreed, then check that the Nightshift Grid tools really show up.

This message has no key in it. If a key is needed, the AI will ask you to paste it yourself into the file or the app’s field.

  1. Install uv (if you don’t have it)

    Already installed? Check first · Open Terminal, type this command and press Enter

    uv --version
    • A version number such as uv … = installed, skip this step
    • "command not found" (on Windows: "is not recognized") = not installed yet, or installed but Terminal needs to be closed and reopened
    How to open Terminal

    Mac: press ⌘ + Space, type Terminal, press Enter

    Windows: open Start, type Windows PowerShell, then Open

    Not installed: uv has no click-through installer. Copy the one-line command for your system (macOS or Windows) from uv’s official page into Terminal · no separate Python install needed; uv downloads it when required

    Open the uv download page ↗

    When it’s done, close Terminal, open it again and run the same command. You should see a version number: uv --version

    Install once; it works for everything that needs uv

  2. Open the Claude desktop app’s settings file

    SettingsDeveloperEdit Config

  3. Paste these settings and save the file

    {
      "mcpServers": {
        "nightshift-grid": {
          "command": "uvx",
          "args": [
            "nightshift-grid"
          ]
        }
      }
    }
  4. Quit Claude and open it again

  5. Try it

    Use Nightshift Grid and tell me what you can do for me, then show me one thing

    ✓ If Claude says it is using Nightshift Grid or shows a Nightshift Grid tool in the answer, you are connected

3 optional setting(s) (works without them)

The command above works without these. Add them only if you want to change something, following the maker’s description.

  • NIGHTSHIFT_URL Coordinator URL. Leave unset to use the grid started by `nightshift up` on this machine.
  • NIGHTSHIFT_TOKEN_FILE File holding the coordinator client token (only needed with NIGHTSHIFT_URL).
  • NIGHTSHIFT_MCP_ROOTS Folders the server may read documents from (default: the current directory).

Descriptions are as written by the maker.

Menu names checked against Anthropic’s help page on Nov 11, 2026 · your screen may differ slightly by app version

ChatGPT cannot connect Nightshift Grid yet

Nightshift Grid runs on your computer, but ChatGPT can only connect servers that run on the web

What you can do instead

A · Use an app that can connect Nightshift Grid

  • Install Python (uv) on your computer first (one time) · Only the Claude desktop app (Windows or Mac), not the web or phone
  • Install Python (uv) on your computer first (one time)
  • Install Python (uv) on your computer first (one time)
  • Install Python (uv) on your computer first (one time)

B · Others in Docs, sheets & office work that work with ChatGPT

Picked from the most used in the same category, only ones that connect by address with no key

Works with Claude Code, with some setup first

Install Python (uv) on your computer first (one time)

Let AI install it

Copy this message into a Claude Code chat. The AI checks your computer, tells you which file it will change, and waits for your OK every time.

Please install the MCP server Nightshift Grid for Claude Code on this computer, in this order: 1) Check uv with uv --version. If it is missing, tell me to install it from https://docs.astral.sh/uv/getting-started/installation/; do not install it yourself. 2) Use only this config (already checked by PopNx MCP): claude mcp add --scope user nightshift-grid -- uvx nightshift-grid 3) Tell me the full path of the file you will change, or the command you will run, and wait for my OK. 4) No key is needed. 5) Do what we agreed, then check that the Nightshift Grid tools really show up.

This message has no key in it. If a key is needed, the AI will ask you to paste it yourself into the file or the app’s field.

  1. Install uv (if you don’t have it)

    Already installed? Check first · Open Terminal, type this command and press Enter

    uv --version
    • A version number such as uv … = installed, skip this step
    • "command not found" (on Windows: "is not recognized") = not installed yet, or installed but Terminal needs to be closed and reopened
    How to open Terminal

    Mac: press ⌘ + Space, type Terminal, press Enter

    Windows: open Start, type Windows PowerShell, then Open

    Not installed: uv has no click-through installer. Copy the one-line command for your system (macOS or Windows) from uv’s official page into Terminal · no separate Python install needed; uv downloads it when required

    Open the uv download page ↗

    When it’s done, close Terminal, open it again and run the same command. You should see a version number: uv --version

    Install once; it works for everything that needs uv

  2. Open Terminal

    Mac: press Command+Space and type Terminal · Windows: open PowerShell

  3. Paste this command and press Enter

    claude mcp add --scope user nightshift-grid -- uvx nightshift-grid
  4. Type /mcp in Claude Code

    You should see Nightshift Grid listed as connected

  5. Try it

    Use Nightshift Grid and tell me what you can do for me, then show me one thing

    ✓ If Claude Code says it is using Nightshift Grid or shows a Nightshift Grid tool in the answer, you are connected

3 optional setting(s) (works without them)

The command above works without these. Add them only if you want to change something, following the maker’s description.

  • NIGHTSHIFT_URL Coordinator URL. Leave unset to use the grid started by `nightshift up` on this machine.
  • NIGHTSHIFT_TOKEN_FILE File holding the coordinator client token (only needed with NIGHTSHIFT_URL).
  • NIGHTSHIFT_MCP_ROOTS Folders the server may read documents from (default: the current directory).

Descriptions are as written by the maker.

Menu names checked against Anthropic’s help page on Nov 11, 2026 · your screen may differ slightly by app version

Works with Cursor, with some setup first

Install Python (uv) on your computer first (one time)

Let AI install it

Copy this message into a Cursor chat. The AI checks your computer, tells you which file it will change, and waits for your OK every time.

Please install the MCP server Nightshift Grid for Cursor on this computer, in this order: 1) Check uv with uv --version. If it is missing, tell me to install it from https://docs.astral.sh/uv/getting-started/installation/; do not install it yourself. 2) Use only this config (already checked by PopNx MCP): { "mcpServers": { "nightshift-grid": { "command": "uvx", "args": [ "nightshift-grid" ] } } } 3) Tell me the full path of the file you will change, or the command you will run, and wait for my OK. 4) No key is needed. 5) Do what we agreed, then check that the Nightshift Grid tools really show up.

This message has no key in it. If a key is needed, the AI will ask you to paste it yourself into the file or the app’s field.

  1. Install uv (if you don’t have it)

    Already installed? Check first · Open Terminal, type this command and press Enter

    uv --version
    • A version number such as uv … = installed, skip this step
    • "command not found" (on Windows: "is not recognized") = not installed yet, or installed but Terminal needs to be closed and reopened
    How to open Terminal

    Mac: press ⌘ + Space, type Terminal, press Enter

    Windows: open Start, type Windows PowerShell, then Open

    Not installed: uv has no click-through installer. Copy the one-line command for your system (macOS or Windows) from uv’s official page into Terminal · no separate Python install needed; uv downloads it when required

    Open the uv download page ↗

    When it’s done, close Terminal, open it again and run the same command. You should see a version number: uv --version

    Install once; it works for everything that needs uv

  2. Click this button to open Cursor

    Open in Cursor

    Cursor asks you to confirm; click Install

  3. Open the AI chat in Cursor in Agent mode

  4. Try it

    Use Nightshift Grid and tell me what you can do for me, then show me one thing

    ✓ If Cursor says it is using Nightshift Grid or shows a Nightshift Grid tool in the answer, you are connected

3 optional setting(s) (works without them)

The command above works without these. Add them only if you want to change something, following the maker’s description.

  • NIGHTSHIFT_URL Coordinator URL. Leave unset to use the grid started by `nightshift up` on this machine.
  • NIGHTSHIFT_TOKEN_FILE File holding the coordinator client token (only needed with NIGHTSHIFT_URL).
  • NIGHTSHIFT_MCP_ROOTS Folders the server may read documents from (default: the current directory).

Descriptions are as written by the maker.

Menu names checked against Cursor’s help page on Nov 11, 2026 · your screen may differ slightly by app version

Works with VS Code, with some setup first

Install Python (uv) on your computer first (one time)

Let AI install it

Copy this message into a VS Code chat. The AI checks your computer, tells you which file it will change, and waits for your OK every time.

Please install the MCP server Nightshift Grid for VS Code on this computer, in this order: 1) Check uv with uv --version. If it is missing, tell me to install it from https://docs.astral.sh/uv/getting-started/installation/; do not install it yourself. 2) Use only this config (already checked by PopNx MCP): { "servers": { "nightshift-grid": { "type": "stdio", "command": "uvx", "args": [ "nightshift-grid" ] } } } 3) Tell me the full path of the file you will change, or the command you will run, and wait for my OK. 4) No key is needed. 5) Do what we agreed, then check that the Nightshift Grid tools really show up.

This message has no key in it. If a key is needed, the AI will ask you to paste it yourself into the file or the app’s field.

  1. Install uv (if you don’t have it)

    Already installed? Check first · Open Terminal, type this command and press Enter

    uv --version
    • A version number such as uv … = installed, skip this step
    • "command not found" (on Windows: "is not recognized") = not installed yet, or installed but Terminal needs to be closed and reopened
    How to open Terminal

    Mac: press ⌘ + Space, type Terminal, press Enter

    Windows: open Start, type Windows PowerShell, then Open

    Not installed: uv has no click-through installer. Copy the one-line command for your system (macOS or Windows) from uv’s official page into Terminal · no separate Python install needed; uv downloads it when required

    Open the uv download page ↗

    When it’s done, close Terminal, open it again and run the same command. You should see a version number: uv --version

    Install once; it works for everything that needs uv

  2. Click this button to open VS Code

    Open in VS Code

    VS Code asks you to confirm; click Install

  3. Open the AI chat in VS Code in Agent mode

  4. Try it

    Use Nightshift Grid and tell me what you can do for me, then show me one thing

    ✓ If VS Code says it is using Nightshift Grid or shows a Nightshift Grid tool in the answer, you are connected

3 optional setting(s) (works without them)

The command above works without these. Add them only if you want to change something, following the maker’s description.

  • NIGHTSHIFT_URL Coordinator URL. Leave unset to use the grid started by `nightshift up` on this machine.
  • NIGHTSHIFT_TOKEN_FILE File holding the coordinator client token (only needed with NIGHTSHIFT_URL).
  • NIGHTSHIFT_MCP_ROOTS Folders the server may read documents from (default: the current directory).

Descriptions are as written by the maker.

Menu names checked against VS Code’s help page on Nov 11, 2026 · your screen may differ slightly by app version

Other apps that use MCP, such as Windsurf, Zed or Gemini CLI, each add servers differently. See how in the app list.

See every app that uses MCP →

JSON settings are under “For developers” below

Stuck? Ask people who use Nightshift Grid💬 Discussion →
For developers: Terminal commands and JSON settings

Installed on your computer

Claude Code

claude mcp add --scope user nightshift-grid -- uvx nightshift-grid

Claude Desktop (claude_desktop_config.json)

{
  "mcpServers": {
    "nightshift-grid": {
      "command": "uvx",
      "args": [
        "nightshift-grid"
      ]
    }
  }
}

Cursor (~/.cursor/mcp.json)

{
  "mcpServers": {
    "nightshift-grid": {
      "command": "uvx",
      "args": [
        "nightshift-grid"
      ]
    }
  }
}

VS Code (mcp.json)

{
  "servers": {
    "nightshift-grid": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "nightshift-grid"
      ]
    }
  }
}

Values you fill in

  • NIGHTSHIFT_URL env
    Coordinator URL. Leave unset to use the grid started by `nightshift up` on this machine.
  • NIGHTSHIFT_TOKEN_FILE env
    File holding the coordinator client token (only needed with NIGHTSHIFT_URL).
  • NIGHTSHIFT_MCP_ROOTS env
    Folders the server may read documents from (default: the current directory).

Descriptions are as written by the maker.

These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.

At a glance

Downloads per weeki
179/wk
Licencei
Apache-2.0
Connection
Runs on your computer
Latest versioni
0.1.3
Published to registryi
Nov 15, 2026
Code last changedi
Nov 15, 2026
Maker
redd34
Packages
pypi: nightshift-grid
Website
github.com
Registry status
Active

Which apps can use it

Based on how this server connects and on each app’s own docs, checked Nov 10, 2026.

Run on your computer in

ClaudeGooseLM StudioMsty StudioCherry StudioCursorVS Code + GitHub CopilotVisual StudioWindsurf (Devin Desktop)ZedKiroClineContinueJetBrains AI AssistantClaude CodeCodex CLIGemini CLIOpenCodenodecodeWarpLibreChatRaycast

All apps, with pros and cons →

Related guides

What it can do

Runs on your computer; the tool list appears in your AI app after you install it.

Basic checksi

We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 20, 2026

  • ✓ Pass

    Maker matches the repo

    The registry name was verified with the GitHub account redd34, which owns the repo

  • ✓ Pass

    Still maintained

    Code last changed 5 days ago

  • ✓ Pass

    Has a licence

    Uses Apache-2.0

  • – Not applicable

    Endpoint responds

    This one runs on your computer; there is no internet endpoint

  • – Not applicable

    Sign-in with OAuth

    Runs on your computer and uses local settings instead

  • … Not checked yet

    No hidden instructions in tool descriptions

    Runs on your computer; we can only read tool lists from internet endpoints

Published vulnerabilities (OSV.dev)

No entries on OSV.dev for nightshift-grid@0.1.3

Checks only this package version, not every dependency · checked Nov 15, 2026

What we check → · JSON

Makers: ask for a re-check or report wrong info
For makers: add a badge to your README

If you made this, paste this code into your README. The badge links back to this page.

[![Featured on PopNx MCP](https://mcp.popnx.com/badge/redd34-nightshift-grid.svg)](https://mcp.popnx.com/en/servers/redd34-nightshift-grid)

Discussion

Ask, share a tip or report that it does not work. Sorted by what people marked helpful.

No posts yet. Be the first to ask or share.

Posts here are written by users, not the PopNx team.

Sign in to post

User reviews

No reviews yet

Sign in to write a review

Compared with others in Docs, sheets & office worki

  • More stars than 81% of the other 4164 servers in this category
  • Published to the registry more recently than 86% of the other 4164 servers in this category
  • Basic checks equal to or better than 99% of the other 4164 servers in this category

Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.

Common questions

Is Nightshift Grid safe?

It passed 3 of 3 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.

What keys or codes does it need?

The registry does not list a required key, though some servers ask you to sign in on first use.

Does it run on my computer or in the cloud?

It runs on your computer. Your AI app starts it when needed, and data does not pass through the maker’s servers (unless it calls an online service itself).

Is it still maintained?

The GitHub repo last changed 5 days ago, and the latest version (0.1.3) reached the registry 5 days ago.

Which apps can use it?

Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need Python (uv) on your computer.

What can I use instead?

In the same category: Puter MCP, XcodeBuildMCP, Vexa, Atlassian Rovo MCP Server, Anki MCP Server

Similar alternatives

Same category, other makers, commands already checked. Official ones first, then by stars.

Reading a card:↓ Downloads per weeki★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi

Puter MCP

Puter MCP enables AI tools to interact with Puter: manage files, websites, workers, and more

by HeyPuterWidely used★ 44.2KUpdated 5 months ago

Runs in the cloud✓ service owner · puter.com

XcodeBuildMCP

XcodeBuildMCP provides tools for Xcode project management, simulator management, and app utilities.

by getsentryWidely used↓ 130.5K/wk shared package★ 6.6KUpdated 4 months ago

Runs on your computer✓ service owner · xcodebuildmcp.com

Vexa

Meeting bot and transcripts for Google Meet, Teams and Zoom. Live or after, speakers labelled.

by Vexa-aiWidely used★ 3KUpdated 2 months ago

Runs in the cloud✓ service owner · vexa.ai

Atlassian Rovo MCP Server

Atlassian’s official server lets AI search and manage Jira work and Confluence pages. Connects to Atlassian’s cloud with OAuth sign-in.

by atlassianGrowing★ 1.2KUpdated 2 months ago

Runs in the cloud✓ service owner · atlassian.com

Anki MCP Server

MCP server for Anki flashcards: adaptive review, notes, media, and deck management via AnkiConnect.

by ankimcpGrowing↓ 1.1K/wk★ 570Updated 2 months ago

Runs on your computer✓ service owner · ankimcp.ai
Compared with similar ones
This one
Nightshift Grid
Puter MCPXcodeBuildMCPVexaAtlassian Rovo MCP ServerAnki MCP Server
Runs whereInstalls on your computerRuns in the cloud, nothing to installInstalls on your computerRuns in the cloud, nothing to installRuns in the cloud, nothing to installInstalls on your computer
Needs a keyNoNoNoYesNoNo
Add with + in ClaudeNoNoNoNoYesNo
Basic checks3/34/43/32/44/43/3
LicenseApache-2.0AGPL-3.0MITApache-2.0Apache-2.0MIT
PriceNo cost listed in the registryNo cost listed in the registryNo cost listed in the registryNo cost listed in the registryNo cost listed in the registryNo cost listed in the registry

README from the maker

Open the README

Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.

Nightshift Grid ⚡️

Turn idle laptops, office PCs and legacy mini-PCs into a zero-CapEx, fault-tolerant local AI batch and GraphRAG cluster.

pipx install nightshift-grid     # or: uv tool install nightshift-grid

nightshift up --mock --workers 3 # coordinator + 3 workers + live dashboard

A real (mock-inference) run recorded with scripts/record_demo.py. Benchmarks so far are from a single Mac; see Known limitations.

Nightshift Grid is a lightweight distributed compute engine ("SETI@home meets local enterprise MapReduce"). It harvests idle cycles across mixed local machines without slowing down the people using them.

It doesn't slice one giant model across slow LAN links, where Wi-Fi jitter destroys token throughput and one closed laptop lid kills the forward pass. Instead, every machine is a preemptible, fenced micro-worker running its own quantized small model (qwen3:4b, qwen2.5:3b, phi4-mini) via Ollama. A central coordinator hands out leased chunks. When a human touches the machine, the node yields immediately and its chunk moves to another node.

           submit 24 chunks                      output_graph.jsonl

client ──────────────────────▶ Coordinator ───────────────────────▶ (1 record / chunk) │ ▲ lease(task_id, lease_id) / heartbeat 3s / complete / preempt ┌───────────────┼──┼────────────────┐ ▼ ▼ │ ▼ node-office-pc node-legacy-laptop node-mac-studio each: worker_daemon.py (Tier 2) (Tier 1) (Tier 3) + local Ollama


Why this exists

Most teams have gigabytes to terabytes of unstructured PDFs, logs and tickets that can't go to cloud APIs for cost or privacy reasons. Meanwhile the office PCs, laptops and mini-PCs that could process them sit mostly idle all day and fully idle overnight.

The common ways to pool local machines leave a gap for batch pipelines:

ApproachTypical failure mode for batch workNightshift Grid
Tensor/layer splitting (one big model sharded across machines)Bound by LAN serialization. One node dropping mid-pass stalls the whole request.Each node runs a whole small model on independent chunks. A dropped node costs one chunk retry.
Stateless request routing (load-balance chat requests across nodes)No durable job state, so a node dying mid-request fails that request.Stateful MapReduce queue with fenced leases. Every chunk completes or is explicitly dead-lettered.
Dedicated inference poolsMachines must be handed over to the cluster.Good-citizen harvesting: the human always wins and the grid backs off in milliseconds.

Capability tiers decide what each node gets: Tier 1 (<8GB free) does embeddings and chunking, Tier 2 (8–24GB) does 3B–8B INT4 entity/relationship extraction, and Tier 3 (>24GB, or Apple Silicon with ≥16GB free) does heavy verification and synthesis.


Key highlights and live benchmarks

1. Sub-250ms GPU yield, including during model load and prompt eval

A common trap when wrapping Ollama or llama.cpp in Python is breaking out of the token loop without closing the underlying socket. The server keeps generating, and the GPU stays pegged until the response finishes. A second trap is checking for user activity only when a token arrives. That leaves a blind spot while the model is loading weights or evaluating a long prompt.

Nightshift runs inference in its own asyncio task. An out-of-band activity watcher polls the chaos trigger file every 100ms and OS HID idle time every 500ms: IOKit HIDIdleTime read in-process on macOS (ioreg -c IOHIDSystem as a fallback), GetLastInputInfo on Windows, D-Bus or xprintidle on Linux. On activity it calls task.cancel(), which unwinds async with client.stream(...) and closes the connection, so Ollama stops generating.

Measured with qwen3:4b on Apple Silicon (GPU utilisation from IOKit, 250ms samples):

Worker cancellation methodGPU utilisation afterwards
Stop the read loop, leave the response open84–94% until the model finishes
Error raised inside async with client.stream0% by the first sample; next request ready in 0.04s
Out-of-band task.cancel() (also covers model load and prompt eval)0% by the first sample
2. End-to-end chaos benchmarks

Three workers (qwen3:4b, about 130 tok/s decode) processed a 24-chunk industrial-maintenance GraphRAG extraction job per phase, with auth enabled (python nightshift.py chaos-test --model qwen3:4b). All three workers ran on one Mac sharing one Ollama instance. Multi-machine runs are still to do.

Chaos scenario / metricMeasured result
Live human preemption (user returns mid-job on node-legacy-laptop)24/24 chunks in 47.3s, 0 failures
Activity → coordinator reclaims the lease (trigger file, 100ms poll)0.01–0.10s across runs (0.011s in the final run)
Lease reclaimed → re-assigned to another node0.8s
Activity → preempted chunk finished on the backup node5.2s
Work sent to the paused node while the human is active0 chunks
Worker crash (SIGKILL node-office-pc mid-chunk)24/24 chunks in 45.8s
SIGKILL → lease expiry (12s TTL) → re-assigned → done11.9s → +1.1s → 16.8s total
Coordinator crash (SIGKILL coordinator mid-job, 3s outage, restart on same SQLite file)24/24 chunks in 46.4s, 24 attempts for 24 chunks (0 wasted)
Restart → ready; in-flight leases finished by their original holders0.23s; 2/2
Host CPU spike (busy-loop on all 16 cores mid-job, --max-host-cpu-pct 65)24/24 chunks in 54.4s; all 3 workers yielded (cpu_busy) in 1.9–2.7s, 0 leases while loaded, all resumed 2.1s after the load stopped
Unintended preemptions from the grid's own Ollama load (phases 1–3)0
Auth (anonymous submit / worker token on client API / forged completion)401 / 401 / 401
Output integrity (4 jobs)96/96 records, 0 missing, 0 duplicates, 434 triples

With --native-idle-seconds, detection latency is bounded by the 500ms HID poll rather than the 100ms file poll. The HID path is covered by unit tests and live IOKit and ioreg reads. An end-to-end benchmark with real keyboard input is still to do, because synthesising HID events needs macOS Accessibility permission.


Core guarantees

GuaranteeMechanism
No chunk lostEvery lease has a 12s TTL, extended by 3s heartbeats, and a reaper re-queues expired leases. Preemption and graceful SIGTERM hand leases back immediately. A worker can hold only one lease at a time.
Fenced leases (no split-brain)Each assignment carries a unique lease_id. A partitioned or stalled worker can't heartbeat or complete a lease that was re-issued. The heartbeat reply (lease_valid: false) tells it to abort the zombie compute.
Race-free pull and pauseIf a human returns while a pull is in flight, the new lease goes straight back. Preempt messages name their lease, so a late one can't revoke a newer lease. A paused node gets no work until it reports idle.
Dead-letter protectionErrors and lease expiries count toward MAX_FAILURES=3, after which the chunk is parked as FAILED. Human preemptions don't count as failures.
Clean graph outputOllama structured outputs (a JSON schema) constrain decoding. normalize_extraction() coerces the output to [subject, RELATION, object] and canonicalises relation names (exceeded during → EXCEEDED_DURING) so edges merge across chunks. Reasoning tokens are disabled on thinking models (qwen3). Invalid output is a retryable failure.
Idempotent sinkoutput_graph.jsonl is fsynced per record and deduplicated by task_id, including across a coordinator restart or a failed fsync. Retried completions are no-ops.
Capability-aware schedulingA worker serves the highest tier it's capable of first, so Tier 3 nodes aren't spent on Tier 1 work while Tier 3 work waits. Recovered chunks go to the front of the queue.
Survives coordinator crashesEvery state transition is journaled to SQLite (WAL) in one transaction. On restart, queue order, results and dead letters are recovered, and in-flight leases get a fresh TTL so workers that kept computing can still complete them. Workers retry completions for 30s to ride out the restart. About 11k durable transitions/s; a 50k-task job recovers in 0.3s.
Least-privilege authSeparate bearer tokens for workers (/worker/*) and clients (/v1/*), so a compromised laptop can lease work but can't submit jobs or read results. Each worker registration gets a session secret (X-Nightshift-Session), so a live worker's id can't be hijacked. Constant-time comparison. Tokens come from files or env, never argv. Reused token files must be regular, owned by you and 0600 (no symlinks). The coordinator binds loopback by default and refuses a LAN bind without tokens. Browser Origin requests are refused, and in no-auth loopback mode untrusted Host headers are refused too (DNS-rebinding protection).
Good citizen beyond the keyboardWorkers also pause on battery power (--allow-battery to opt out) and under thermal throttling (macOS pmset, Linux sensors). They pause when *other* processes push host CPU over --max-host-cpu-pct (default 65; Ollama and co-located workers are excluded; sustain and hysteresis prevent flapping; the full process table is walked only every 30s, with new processes picked up on every 1s poll). They pause when free RAM drops under --min-free-ram-gb (default 2.0), evicting the model with keep_alive: 0; the resume threshold includes the model's size, so unloading can't cause a pause/reload loop.
Fail-closed idle sensingWith --native-idle-seconds, a worker that can't read HID idle time refuses to start (--allow-no-idle-sensor overrides). Sensors: macOS IOKit HIDIdleTime in-process (falling back to ioreg), Windows GetLastInputInfo, GNOME/Wayland Mutter and freedesktop ScreenSaver over D-Bus, X11 xprintidle. If a sensor dies at runtime, the worker pauses (idle_sensor_lost) rather than guessing.
Zero-config LAN discoveryworker_daemon.py --discover finds the coordinator over UDP broadcast. The reply carries an HMAC proof keyed by the worker token, so a rogue host can't impersonate the coordinator and harvest tokens. Replays fail (fresh nonce), two valid coordinators are an error, and responses are size-capped and rate-limited (not an amplifier).
Live vector index (optional)--qdrant-url adds a Qdrant sink alongside the always-on JSONL. Writes are queued off the event loop, batched, embedded (nomic-embed-text, or a deterministic hash embedder) and upserted idempotently into nightshift_graph. Failures spool to disk and replay, and never fail a completion. One embedder per collection is enforced.

| Preemption without lost work (Baton relay, opt-in) | With coordinator.py --relay

Only the beginning is shown; read the rest in the repo