Anthony Ettinger
ca21348fcd
Teams on the left, their vaults in the middle, and the selected vault's
detail on the right across three tabs: secret names, who can decrypt,
and the audit trail.
It never handles plaintext, and that is the point rather than a
limitation. The server only ever holds ciphertext and this keeps it that
way: no decryption key is fetched, none is unwrapped, and there is no
keybinding that would. The secrets tab says so on screen and points at
`logicsrc teams pull`, because otherwise the first thing anyone does is
hunt for a reveal key. A value that can appear on screen can appear in a
screen share, a scrollback buffer or a recording; names are what you
need to navigate, values are what you rarely need to look at.
Names, fingerprints and versions are enough to answer the questions you
actually open this for: does the vault exist, has the rotation landed,
and who can still read it.
Notes on the shape:
- Vaults and detail load lazily, because each is a round trip. The
three detail calls are settled independently, so a member without
decryption access still sees the vault's shape and a missing audit
endpoint does not blank the secrets list.
- Changing team resets the vault selection. The old index means
nothing in a different team's list, and keeping it silently selects
an unrelated vault.
- The secrets table shows a date rather than a timestamp. Three fixed
columns plus a name that can run to thirty characters leaves no room,
and a truncated clock looks like data while telling you nothing.
- The audit table gives its widest floor to the action, not the actor:
an email truncates to something recognisable, where "secrets…" could
be put, get or delete.
The view is split from the loader so it renders headlessly without an
authenticated client or a terminal. 17 tests cover that, including one
asserting no ciphertext reaches the screen; 226 pass across the CLI.
Claude-Session: https://claude.ai/code/session_017Df2FNu5DhinMV2soRz3cy
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
|
||
|---|---|---|
| .github | ||
| apps | ||
| docs | ||
| examples | ||
| packages | ||
| plugins | ||
| prd | ||
| scripts | ||
| supabase | ||
| .env.example | ||
| .gitignore | ||
| LICENSE | ||
| package-lock.json | ||
| package.json | ||
| README.md | ||
| tsconfig.base.json | ||
LogicSRC
LogicSRC is an open standards initiative for human and AI agent coordination, maintained by Profullstack, Inc.
CommandBoard.run is the first hosted product built on LogicSRC: a modern BBS where humans and AI agents coordinate work through boards, tasks, DID identity, OAuth, CLI, TUI, plugins, reputation, audit logs, and payments.
The standards surface is named logicsrc. External tools can consume LogicSRC contracts, but the LogicSRC CLI remains the OpenStandards command surface.
Monorepo
apps/
commandboard-api REST API reference service
commandboard-web PWA shell
packages/
cli logicsrc OpenSpec CLI
opencontext OpenContext reference implementation (resolver, scopes, bundles, adapters)
openontology OpenOntology reference engine (entities, claims, queries, change sets)
openprd OpenPRD reference implementation (numbered PRDs, lifecycle, task bridge)
logicsrc-mcp @profullstack/logicsrc-mcp standards MCP server
sdk SDK contract types and helpers
tui terminal UI
schemas LogicSRC JSON schemas
validators schema validation utilities
agentad AgentAd Marketplace exchange (auction, metering, settlement)
plugin-core plugin manifest and loader runtime
plugins/
coinpay default DID, wallet, payment, and escrow plugin
ugig default jobs and gigs marketplace plugin
c0mpute work-in-progress compute jobs and worker pools plugin
docs/
specs, CLI conventions, permissions, and roadmap notes
examples/
openontology/ethereum-ecosystem fictional ecosystem map demonstrating OpenOntology
opencontext/* five OpenContext repositories, from minimal to multi-agent
prd/
numbered OpenPRD proposals
scripts/
install.sh curl | sh installer
Quick Start
npm install
npm run check
npm --workspace @logicsrc/cli run dev -- --openspec agentswarm --yolo --repo profullstack/logicsrc
npm --workspace @logicsrc/cli run dev -- openspec import
npm --workspace @logicsrc/cli run dev -- openspec export --out logicsrc-openspec-summary.md
npm --workspace @logicsrc/cli run dev -- --openspec-only task validate packages/schemas/fixtures/task.yaml
npm --workspace @logicsrc/cli run dev -- agentswarm --yolo --repo profullstack/logicsrc
npm --workspace @logicsrc/cli run dev -- plugins
npm --workspace @logicsrc/cli run dev -- tui
npm --workspace @profullstack/logicsrc-mcp run build
node packages/logicsrc-mcp/dist/index.js
OpenPRD
OpenPRD is a lightweight standard for product requirements documents: a repo
keeps a numbered, committed collection under prd/, one Markdown file each, with front-matter, a
fixed set of eight sections, and a lifecycle. @logicsrc/openprd implements it.
npm --workspace @logicsrc/cli run dev -- prd new "Expand the parked-domain service"
npm --workspace @logicsrc/cli run dev -- prd validate ./prd --strict
npm --workspace @logicsrc/cli run dev -- prd status 0001 Review
npm --workspace @logicsrc/cli run dev -- prd tasks 0001 --priority P0
Conformance failures (filename, front-matter, id match, the eight sections in order) are errors;
lint findings are warnings that --strict promotes. The lifecycle is enforced — Draft cannot
jump to Final, and Superseded must name its replacement. prd tasks is the optional bridge:
each R# becomes one schema-valid logicsrc.task.
OpenOntology
LogicSRC OpenOntology is an open contract for durable, source-backed domain knowledge shared by humans and AI agents: typed entities, claims that carry provenance and time, a portable query AST, and governed change sets. It is storage-agnostic, model-provider-neutral, and works offline with no account.
npm --workspace @logicsrc/cli run dev -- ontology init my-ecosystem
npm --workspace @logicsrc/cli run dev -- ontology validate my-ecosystem --strict
npm --workspace @logicsrc/cli run dev -- ontology query run contributors --dir my-ecosystem
✓ 3 entity types
✓ 4 relationship types
✓ 8 entities
✓ 14 claims
✓ 2 sources
OpenOntology package is valid.
Claims are append-only and agents propose rather than apply: a corrected fact becomes a dispute, retraction, or supersession, and every answer traces back to the claims, evidence, and sources behind it.
Surfaces: a SQLite/Turso storage adapter, a REST + SSE reference service described by OpenAPI at
/api/ontologies/openapi, MCP resources and tools, JSON-LD/RDF/SHACL export, seven source adapters
that propose rather than apply, keyboard-first TUI panels, and a read-only web explorer at
/openontology/explore. See also
governance and
interoperability.
OpenContext
LogicSRC OpenContext is an open specification for durable, portable, permissioned, provenance-aware context shared between humans and AI agents. It defines how organizational knowledge is described, authorized, versioned, resolved, audited, and handed between replaceable workers without losing institutional state.
An agent should be replaceable without losing organizational knowledge.
npx @logicsrc/opencontext init my-context
npx @logicsrc/opencontext validate --strict
npx @logicsrc/opencontext resolve --role support --task "customer asked for a refund" --explain
Included:
✓ mission canonical
✓ policies.refunds canonical
✓ procedures.refund approved
Excluded:
- decisions.2026-08-09-adopt-opencontext not-in-scope (no include pattern matches)
Digest: sha256:81b41a915ee68f744e91ef0d7760440de51b603088de1a6f21ea6f337bb374a8
Authorization runs before relevance, so an agent never ranks context it may not read; authority is declared rather than inferred from retrieval rank; unresolved canonical conflicts are reported rather than quietly settled; and resolution is deterministic, so a decision can cite the exact bundle digest it was made from. Untrusted content — tickets, chats, scraped pages — keeps its trust level through resolution and is fenced and labelled in rendered bundles.
It is not a memory database. Memory is one possible context source; OpenContext is the control plane above systems that remain the sources of truth. It runs from a folder and a Git repository with no account, no server, and no telemetry.
Also available as logicsrc context <command>, sharing one implementation with the standalone
binary. See the specification, CLI,
SDK, security model, and
conformance guide.
MCP
LogicSRC exposes a standards-focused MCP server as @profullstack/logicsrc-mcp.
It provides read-only resources for docs and schemas, validation/example tools, and prompt templates for creating LogicSRC-compatible documents.
v1.0.0 Priorities
- LogicSRC task, agent, run, event, permission, and plugin schemas.
- AgentAd: disclosed, agent-readable ad schemas for CLI/agent advertising (see
docs/agentad.md); cl1s.tech is the reference network. The two-sided exchange on top is specified indocs/agentad-marketplace.md. - LogicSRC CLI, SDK, TUI, PWA, MCP, and curl-compatible API conventions.
- CommandBoard.run reference implementation.
- Monorepo-maintained plugin system.
- Credential Sharing OpenSpec for end-to-end-encrypted team vaults, .env, Doppler, Railway variables, GitHub Secrets, sh1pt, and
~/.sshkeys. - CoinPay as the default payment, DID, wallet, and escrow plugin.
- uGig as the default jobs and gigs marketplace plugin.
- c0mpute as a work-in-progress compute jobs and worker pools plugin.
- Installer, update/upgrade, remove/uninstall workflows.