Verified project context

Stop making models relearn the repository.

Give them the project truth they actually need.

Atlas compiles current repository evidence into a bounded working set any coding agent can use.

Layered paper, glass, and metal arranged into a compact evidence stack

Local-firstProject source stays under your control.

Provider-neutralOne evidence layer for any model or agent.

CLI + MCPShared contracts across human and agent workflows.

Dual licensedMIT or Apache-2.0.

Every new session pays the rediscovery tax.

Agents list directories, search broad terms, reopen the same files, and reconstruct relationships that the last session already found.

That cost is larger than tokens.

Partial scans and stale assumptions become confident changes.

Atlas makes project understanding persistent, qualified, and bounded to the task at hand.

Compile project truth once. Serve only what the task needs.

Atlas keeps verified evidence persistent, then assembles a small working set from one immutable generation.

  1. Repository state
    Source History Tests Diagnostics
  2. Truth Plane Qualified project evidence

    Files, revisions, symbols, relationships, effects, coverage, conflicts, and lifecycle history.

  3. Context IR Minimum sufficient working set

    Generation-bound evidence with selection reasons, costs, omissions, and uncertainty intact.

  4. Outcome Any model or agent

    Works from current evidence without rescanning the whole repository.

Technical papers sorted from broad research into a precise central evidence set

Evidence stays qualified.

Atlas does not replace source, builds, tests, or runtime evidence. It records where evidence came from and whether it is current, verified, unresolved, conflicting, stale, omitted, or unavailable.

Freshness
Live source checks block stale change-mode use.
Boundaries
Fixed budgets keep task context controlled and inspectable.
Failure
Failed candidates never partially replace the last valid generation.

A clear path from local source to shared engineering context.

Open source users

Build locally. Inspect every contract.

The release candidate is source-built, local-first, provider-neutral, and dual licensed. Public repository access is being prepared.

cargo build --release --locked
atlas init <repository>
atlas reconcile <repository>
Open GitHub (access required)

Engineering teams

Integrate one evidence contract across tools.

Use CLI and MCP surfaces to share deterministic, generation-bound context without coupling Atlas to one model provider.

Review operations

Commercial and research partners

Test the context question that matters.

Run pilots around context yield, accepted-task usefulness, and integration with real engineering workflows. No model lock-in is required.

Contact project owner

Release boundary

Shipped capabilities are separated from the research horizon.

The release candidate already provides persistent project truth, deterministic task compilation, temporal intelligence, and CLI/MCP parity.

Available in the current candidate

  • V1.1Semantic Truth
  • V1.2Context IR + Observability
  • V1.3Deterministic Task Compiler
  • V1.4Temporal Intelligence

Research and future work

  • V1.5Working-Set Optimization
  • V2.0Project Context Compiler

How small can a model's working view become without reducing correctness?

Workspace Atlas turns that question into an inspectable engineering system.