Verchestra
Menu

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.

Explore how it worksView on GitHubFollow the road to 1.0
0.0.0-qualificationT68 verifiedT68a next

Public source development is available. A public installer and production release are not.

Delivery pathportable / signed / reviewable
  1. 01
    RequestA developer brings a real delivery outcome, not a provider-specific prompt.
  2. 02
    DiscoveryRepositories, approved documentation, and read-only data context become source-bound evidence.
  3. 03
    Execution PackageRequirements, decisions, tasks, authority, and completion gates are sealed into a portable contract.
  4. 04
    Qualified driverClaude Code, Codex, or OpenCode/Qwen receives the same bounded delivery contract.
  5. 05
    EvidenceTests, digests, signed reports, and handoff state prove what happened.
  6. 06
    Human 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.

Control where it matters. Freedom where it helps.

Models can change. The delivery contract, evidence, and accountability do not.

01

Portable execution

Move work between qualified environments without transferring credentials or machine authority.

02

Policy before effects

Capabilities, approvals, leases, and egress rules are evaluated before external actions.

03

Read-only discovery

Bounded database probes expose approved context without creating a hidden writer.

04

Evidence, not assertions

Packages, runs, reports, and release inputs bind their source state by digest and signature.

05

Human control

Independent verification and human acceptance remain explicit workflow states.

06

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.

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 discovery
Approved probe surfacemode: read_only
  • SAP ASE / Sybasefirst-class adapter
  • PostgreSQLqualified surface
  • MySQL / MariaDBqualified surface
  • SQL Serverqualified surface
  • Oraclequalified surface
  • SQLitequalified surface
  • MongoDBqualified surface

A delivery control plane, not a model wrapper.

vestra CLIApplication workflowsPolicy-bound orchestration
WorkspaceDriversProbesMemoryEvidenceDistribution
Read the architecture

T68 is evidence. T68a is work.

Foundations through T68 are backed by public validation reports. Self-Test, regression, sealed holdout, platform qualification, and the release decision remain ahead.

T01T68
T68a
T77
View the verified roadmapInspect T68 evidence →

Build the standard with us

AI delivery deserves better evidence.

Explore the architecture, challenge the design, and help qualify the path to 1.0.

Join the discussionContribute