I just released Vincent 0.7.0, and this release marks an important milestone for the project:
Vincent now builds Vincent.
All development on the project now goes through Vincent workflows — from creating an approved GitHub issue through planning, implementation, verification, human gates, merge, and release preparation.
The journey from 0.4.0 to 0.7.0 added quite a bit.
Workflows can declare their expected inputs, including:
Vincent also gained a workflow-authoring skill designed around a principle I care about quite a lot: don't use an AI agent when deterministic automation can do the job better.
Commands and native control flow come first. Agents are used where reasoning is actually required.
Real automation fails.
So Vincent now has mechanisms for continuing rather than throwing work away:
vincent doctor
0.7.0 significantly expands the CLI.
Tasks can now be started idempotently, created from GitHub issues, populated through JSON/stdin, queried through vincent status
, limited with max_cost_usd
, and integrated with notifications.
Logs, transcripts, approvals, retries, repairs and task answers can all be handled without entering the TUI.
The TUI hasn't been neglected either — tasks now open into a dedicated workspace containing steps, attempts, metadata, output and file-grouped diffs.
This is the part I'm most excited about.
My own development workflow now uses Vincent itself:
GitHub issue
↓
planning
↓
implementation
↓
documentation
↓
cross-platform verification
↓
human gates
↓
merge
↓
release audit
Claude Code, Codex or Cursor can provide the inference.
Vincent owns the durable workflow, state and verification around them.
That's the architecture I've been working toward: a local, inspectable and vendor-independent control plane for coding agents.
Vincent is also MIT licensed again.
I wrote a deeper overview of everything that changed between 0.4.0 and 0.7.0 here:
https://blog.lezli01.is-a.dev/blog/vincent-0-7-release/
Feedback and contributions are very welcome.