Portable execution
Move work between qualified environments without transferring credentials or machine authority.
Verified delivery
AI delivery that survives the model, the machine, and the handoff.
Verchestra is a verified AI software-delivery harness. It turns discovery, planning, implementation, validation, and human approval into portable, signed, and reviewable delivery work.
In practice: A developer can begin with one AI environment and hand the next developer an executable contract, verified evidence, and the exact next action — without transferring credentials or relying on chat history.
0.0.0-qualificationT77 verified1.0 decision pendingPublic source development and a published qualification package are available. A production release is not.
Delivery path
portable / signed / reviewable- 01RequestA developer brings a real delivery outcome, not a provider-specific prompt.
- 02DiscoveryRepositories, approved documentation, and read-only data context become source-bound evidence.
- 03Execution PackageRequirements, decisions, tasks, authority, and completion gates are sealed into a portable contract.
- 04Qualified driverClaude Code, Codex, or OpenCode/Qwen receives the same bounded delivery contract.
- 05EvidenceTests, digests, signed reports, and handoff state prove what happened.
- 06Human reviewAn accountable reviewer accepts or rejects evidence after independent verification.
Human accountableEvidence before acceptance
The problem
A chat is not a delivery system.
AI-assisted work disappears into provider sessions, local machines, and undocumented decisions. The next developer inherits a conversation, not an executable contract.
Verchestra makes the durable facts portable while credentials, sessions, and machine authority remain local.
What works today
One honest matrix, straight from the evidence.
Human-readable status first, internal task ids second. Each state has one meaning:available — runnable today from a source checkout of the local alpha. qualified — backed by a public validation report; not yet composed into the cli surface. planned — roadmap work with a declared task; no code is claimed.
| Capability | Status | Evidence |
|---|---|---|
| Workspace initialization (init preview and apply) | available | issue #64 slice A/B |
| Evidence signing-key lifecycle (persist, rotate, revoke) | qualified | T68a |
| Cost and duration budget enforcement | qualified | T68b |
| Declared gate repair loop with human escalation | qualified | T68c |
| Policy boundary: declarative tests and signed bundles | qualified | T68d |
| AI driver adapters (Claude Code, Codex, OpenCode/Qwen) | qualified | driver qualification |
| Read-only database probes (7 engines, fixture-qualified) | qualified | database matrix |
| Signed distribution, activation, and rollback (TUF) | qualified | T66-T68 |
| Self-Test trust domain and doctor --deep | qualified | T69-T72 |
| Public regression campaigns and sealed-holdout promotion | qualified | T73-T74 |
| Platform matrix, release candidate, and the 1.0 decision | planned | T75-T77 |
Control where it matters. Freedom where it helps.
Models can change. The delivery contract, evidence, and accountability do not.
Policy before effects
Capabilities, approvals, leases, and egress rules are evaluated before external actions.
Read-only discovery
Bounded database probes expose approved context without creating a hidden writer.
Evidence, not assertions
Packages, runs, reports, and release inputs bind their source state by digest and signature.
Human control
Independent verification and human acceptance remain explicit workflow states.
Safe repetition
Initialization, effects, Git operations, recovery, and handoff converge idempotently.
Start with one environment. Continue with another.
Example handoff. The receiving developer rebuilds local authority while preserving the signed execution contract.
Source environmentClaude CodeDiscovery · specification
Signed Execution Packagerequirements · evidence · gates
Receiving environmentOpenCode / QwenLocal authority · same contract
- Claude Code
- Codex
- OpenCode / Qwen
Read-only data probes
Context from real systems. No hidden writer.
Database discovery runs through bounded plans, explicit capabilities, audit evidence, and read-only credentials. SAP ASE / Sybase is a first-class adapter, not an afterthought.
Explore database discoveryApproved probe surface
mode: read_only- SQLitefirst-class adapter
- MongoDBqualified surface
- MySQL / MariaDBqualified surface
- Oraclequalified surface
- PostgreSQLqualified surface
- SAP ASE / Sybasequalified surface
- SQL Serverqualified surface
A delivery control plane, not a model wrapper.
vestra CLIApplication workflowsPolicy-bound orchestration
WorkspaceDriversProbesMemoryEvidenceDistribution
T77 is evidence. The signed 1.0 decision is work.
Foundations through T77 are backed by public validation reports. The declared qualification chain is fully verified. The signed promote-or-reject decision a 1.0 release requires has not been made.
T01T77
1.0 decision
What Verchestra is not
Ruled out, in the present tense.
- It is not a public production release - the published npm package installs 0.0.0-qualification, not 1.0.
- It is not a hosted service - everything runs on your own machine.
- It does not transfer provider credentials - a handoff carries evidence and next actions, never sessions or secrets.
- It does not make unapproved paid model calls - a missing provider reports not configured, never a silent pass.
- It does not treat CI as human review - acceptance is an explicit human decision recorded as evidence.
- It does not call same-author checks independent verification - that distinction is stated, not blurred.
- It does not expose unqualified commands - the installed CLI advertises init, self-test, and doctor and nothing else.
Build the standard with us
AI delivery deserves better evidence.
Explore the architecture, challenge the design, and help qualify the path to 1.0.