Skip to content
Agentmart
Submit a tool

AGENTS.md · Intuition-Lab/personal-model

AGENTS.md from Intuition-Lab/personal-model: 141 lines covering Runtime boundary, Commands, Pipeline, Documentation map and more.

Template by Intuition-Lab

IndexedApache-2.0★ 1,328
Write a review

Chalk Labs

Need help deploying AGENTS.md · Intuition-Lab/personal-model?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode, Claude Code. Read the repository before you give any tool access to your data.

curl -fsSL https://raw.githubusercontent.com/Intuition-Lab/personal-model/main/AGENTS.md -o AGENTS.md

Read it and adapt it to your project before use.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

The AGENTS.md file that Intuition-Lab/personal-model (1,328 stars) keeps for coding agents. It has 141 lines in 6 sections: Runtime boundary; Commands; Pipeline; Documentation map; Invariants; Naming and provenance. Use it as a model for your own project's instructions.

Use cases: agent-memory, code-generation

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

What's in it

An AGENTS.md file: instructions coding agents (Codex, Cursor, Copilot, Gemini CLI and others) read before working in a repo.

For
Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode, Claude Code
Length
141 lines
File
AGENTS.md

Sections

  1. Runtime boundary
  2. Commands
  3. Pipeline
  4. Documentation map
  5. Invariants
  6. Naming and provenance

First lines (shown under the repo's Apache-2.0 license)

# AGENTS.md

Orientation for coding agents in `persome-core`. Code is authoritative; the
documents explain its public contract and operational intent.

## Runtime boundary

Persome Runtime is a local-first macOS daemon that observes one real person's
screen context, forms durable state, builds an auditable personal model, and
serves it to MCP clients. The public geometry is Point, Line, Face,
Volume, and at most one Root. `/model` renders the current geometry locally.

This repository owns:

- AX capture and optional, local, subprocess-isolated OCR;
- timeline and deterministic session formation;
- incremental session reduction and personal modeling;
- Markdown/SQLite/evomem storage, provenance, correction, and forgetting;
- the versioned model snapshot, local viewer, REST, and MCP.

It does not own product dashboards, notification/task lifecycles, computer-use
actuation, meeting audio, or evaluation datasets and runners.

- macOS 13+ for live capture; Python 3.12-3.13 via `uv`.
- Package: `src/persome/`; CLI: `persome = "persome.cli:app"`.
- Default data root: `~/.persome`.

## Commands

```bash
uv sync --all-extras
bash install.sh

PERSOME_LLM_MOCK=1 uv run pytest -m "not macos and not integration"
uv run ruff check .
uv run ruff format --check .
uv run python scripts/secret_scan.py
uv run python scripts/pii_scan.py
uv run python scripts/language_scan.py

persome doctor
persome llm setup
persome llm status --check
persome start
persome status
persome stop
persome update
persome mcp
persome model build
persome model status
persome model export
```

Regenerate committed contracts after intentional changes:

```bash
uv run python scripts/regen_openapi.py
uv run python scripts/regen_db_schema.py
uv run pytest tests/test_openapi_drift.py tests/test_db_schema_drift.py -q
```

Commits require DCO sign-off: `git commit -s`.

## Pipeline

There is one production path:

```text
mac-ax-watcher or trusted ingest
  -> S0 debounce/dedup
  -> S1 focused element + visible text + URL
  -> capture buffer
  -> one-minute timeline blocks
  -> deterministic session cuts
  -> five-minute active reducer / event memory
  -> incremental Point/Line modeling
  -> session-end trailing-window finalizer
       -> classifier compatibility/incremental pass
       -> pattern detector
       -> evidence-gated memory_delta + deterministic apply
  -> debounced/daily/explicit structural model build
       -> cases -> Faces -> Volumes -> Root
  -> snapshot / MCP / localhost viewer
```

The windowed modeling service in `writer/agent.py` is shared by active flush,
session-end finalization, retry, safety-net, CLI recovery, and model build.
`sessions.delta_end`, `sessions.modeled_at`, and `session-model.lock` make it
cross-process idempotent. Do not add another session-modeling entrance.

## Documentation map

| Need | Document |
|---|---|
| Installation and release verification | `README.md`, `VALIDATION.md` |
| Public Runtime flow | `ARCHITECTURE.md` |
| Snapshot contract | `MODEL_FORMAT.md`, `docs/model-contract.md` |
| Public MCP contract | `MCP.md`, `docs/mcp.md` |
| Capture through model build | `docs/architecture.md`, `docs/capture.md`, `docs/timeline.md`, `docs/session.md`, `docs/writer.md` |
| Configuration and secrets | `docs/config.md`, `docs/runtime-internals.md` |
| Privacy boundary | `SECURITY_PRIVACY.md` |

Update matching docs in the same change as behavior.

## Invariants

- Use `src/persome/paths.py` for every runtime path. Tests use `ac_root` and
  must never touch the real data root.
- Use `with fts.cursor() as conn:` for SQLite. The store runs in WAL mode.
- All stage LLM calls go through `writer/llm.py`. The selected profile uses
  Anthropic Messages or OpenAI-compatible Chat Completions. Provider, protocol,
  model, endpoint, and key variable name live in `config.toml`; key values
  belong in `<PERSOME_ROOT>/env`, never TOML.
- `install.sh` generates and preserves `PERSOME_SCREENSHOT_KEY`. If encrypted
  screenshot persistence lacks a valid key, omit pixels; never write plaintext.
- Default Point/Line production is the windowed `memory_delta` followed by
  deterministic `delta_apply`: active flushes advance `sessions.delta_end` and
  terminal finalization only catches the trailing window. Do not silently
  reintroduce parallel writers.
- Every modeled object preserves evidence receipts and bitemporal history.
- At most one live Root exists. Missing geometry is `degraded`, never fabricated.
- The HTTP server is loopback by default. Except canonical `GET /health`,
  every REST, viewer, and HTTP MCP route requires the owner-local
  `PERSOME_LOCAL_API_TOKEN` bearer (or the one-use viewer capability); still
  treat local endpoint access as access to personal data.
- Prompt edits follow `docs/prompt-engineering.md`: define an eval criterion,
  then change and verify the smallest prompt surface.
- Live capture uses compiled Swift helpers bundled into the wheel. On supported
  Apple Silicon installs, onboarding enables bundled OCR and requests Screen
  Recording; inference runs in an isolated worker.
- `--capture-only` disables timeline and model-processing tasks, but keeps
  capture, session tracking, reducer recovery/safety net, and configured MCP.

## Naming and provenance

The public Runtime uses Persome names and `PERSOME_*` configuration throughout.
Historical product compatibility belongs in downstream consumers, not in this
repository. Legally required third-party attribution remains in `NOTICE` and
`THIRD_PARTY_NOTICES`. Do not add product-specific ports, launchd labels, paths,
or UI behavior to this Runtime.

Signals

Stars
1,328
Forks
90
Open issues
7
Contributors
9
Last commit (this folder)
Jul 14, 2026 (3 months ago)
Last release
Jul 12, 2026 (3 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
Apache-2.0
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from Intuition-Lab

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get AGENTS.md · Intuition-Lab/personal-model running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying AGENTS.md · Intuition-Lab/personal-model?

CallGet help
Cite this page

AGENTS.md · Intuition-Lab/personal-model. Agent Mart. https://agentmart.dev/templates/intuition-lab-personal-model-agents-md (last updated 2026-10-24)