Intentface OS

Intentface OS speaks MCP and a scoped REST API. A connecting agent orients itself in one call, searches in your team's vocabulary, and reports what it couldn't find. Underneath, a curatorial pass keeps the index in order, and the systems your agents depend on are mounted or synced into the same workspace.

Request early accessSee the first call
  • MCP
  • REST API with OpenAPI spec
  • Scoped, expiring keys

Agent-native

An agent's first call tells it everything

Instead of guessing at filenames, a connecting agent calls orient and gets the actual lay of the land: every folder with summaries, every file with an outline and a stable reference, and the vocabulary this organisation uses, all before reading a single document.

orient()an agent's first call

## Workspace: "Acme"

4 folders, 38 files

### Company/ (3 files)

Brand, pricing, and process reference

- pricing.md [pricing] 84L

Plans, tiers, and discount policy

H1: Pricing > H2: Plans > H2: Discounts

- brand-voice.md [brand-voice] 56L

### Clients/ (12 files)

One folder per client: notes, deals, contracts

## Index (concepts)

412 concepts, maintained automatically

- onboarding — how a new client goes live (about: 5)

- pricing — plans and discount policy (about: 3)

- runbook — operational procedures (about: 4)

Recently added: renewal, support-sla

- Unsure what the workspace calls it? concept_resolve first, then search the canonical.

MCP tool surface
  • orientWorkspace map, file summaries, and the concept index spine
  • searchConcept-aware search across every file
  • read_file, edit_file, createRead and write markdown, single or batched
  • query_db, write_dbQuery and update structured tables with SQL
  • concept_resolve, concept_searchResolve a term to what the workspace actually calls it
  • share_file, submit_feedbackPublish artifacts and report back

The AI Janitor

A workspace that tends itself

Knowledge bases rot when upkeep depends on people remembering to do it. Intentface OS assigns the chore to a curatorial pass that runs quietly in the background: roughly 90% machine, 10% human, and that 10% is veto power, not workload.

Merges and splits concepts

Twin terms that emerged separately become one; overgrown ones split.

Lets noise go dormant

One-off terms and unused concepts stop widening your searches.

Writes scope notes

Important concepts get a one-line definition, backfilled automatically.

Detects conflicts

Two live documents disagree on a fact? It asks exactly one question.

The Janitor suggests, the human disposes. It never deletes and never reverts a human edit.

Your knowledge has a pulse

Every search, read, and edit feeds a live health score, and the agents working in the workspace report what they couldn't find, so gaps surface before any human notices them.

Pulse — workspace healthlast 30 days
71

Search is dragging the score down.

Search42Context83Activity100Structure100

Flagged by agents, tended by agents

content gap2h ago

Searched “parental leave policy”, got nothing — the handbook never covers it.

Workspace agent drafted parental-leave.md — waiting on a publisher.draft ready
outdated1d ago

pricing.md still lists last year's rates next to the new plans.

Superseded the old page and linked it to current pricing.resolved
hard to find3d ago

Took four searches to land on the security overview — no synonyms on the concept.

Added “SOC 2” and “compliance” as synonyms on security.resolved

One score, real evidence

Structure, search, context quality, and activity each score 0 to 100. The composite tells you at a glance what's healthy and what's dragging, with the evidence one click away.

Agents file the friction

When a search comes up empty or a document contradicts itself, the agent doesn't shrug. It flags a content gap or an outdated page through submit_feedback, failed query attached.

And the workspace tends to it

Flagged issues become work: the missing page gets drafted, orphans get linked, the stale copy gets superseded, all done by workspace agents and approved by a human clicking yes.

Connected

A knowledge base shouldn't be an island

Intentface OS doesn't have to contain everything. It has to know where everything is. Mount external sources into the index, sync live systems into local tables, and let concepts point to the workflows and tools that actually get the job done.

asksmountedsyncedpoints toyour agentdocs/*.mdxdeals.dbskill: publish a release

Mounted, not copied

Articles in a GitHub repo, marketing pages, a partner wiki: external sources mount straight into the search index. The content stays where it's authored; agents surface it like any native file.

Synced, not fetched

Sandboxed pipelines pull live systems into local, read-only tables: fast, rate-limit-proof, and when a provider changes, exactly one pipeline needs repair. Pipeline code never sees credentials.

An index of skills

Beyond facts, the index covers skills: meta-knowledge of how things get done and where the pieces live. An agent asking “how do we publish a release?” gets the runbook, the repo, and the right connector, not a guess.

  • Slack
  • Clockify
  • Zero CRM
  • Circleback
  • Perplexity
  • External mounts, webhooks, and more

Point your agent at the workspace. It will know where to start.

Claude Desktop, Claude Code, any MCP client, or your own code against the API: the first call is orient, and the rest follows.

Request early accessEverything in Intentface OS

The agent-native side of Intentface OS. Built and run by Intentface.