opencompany
AI workspace with chat, durable tasks, integrations and a wiki whose approval review for workspace actions runs through Jev.
Overview
opencompany is an AI workspace offering chat, durable tasks and workflows, connected integrations, a wiki knowledge base and cloud coding sessions. It is a Bun and Turborepo monorepo: a Next.js web client on Vercel, a Hono API and a Fastify durable runner on Render, Neon Postgres via Drizzle, WorkOS authentication, Electric live read models and Vercel AI Gateway in front of model providers.
Per the list summary, its approval review runs through Jev, so workspace actions are gated by a typed decision. The fetched README excerpt does not describe the approval questions or thresholds, so those details are inferred. The README notes the setup path is maintainer-oriented and requires managed credentials.
What the decision model decides
| Type | Question | Answers |
|---|---|---|
| Yes / no | Should this workspace action be approved?(inferred) | approve · reject |
How it works
- Agent proposes a workspace action.
- Approval review asks Jev a typed question.
- Approve automatically or route for review based on the answer.
Strengths
- Typed approval decisions for agent actions.
Caveats
- Jev usage details only from the list summary.
- Local development requires maintainer credentials.
Getting started
bun install && bun run setup && bun run dev:web (maintainer setup).At a glance
- Type
- Project
- Status
- production
- Language
- TypeScript
- Runtime
- Next.js, Hono, Fastify
- Has code
- yes
Use cases and integrations
How curated lists describe it
Agent workspace: runs its approval review through Jev so workspace actions are gated by a typed decision.
yibie/awesome-jev
Frequently asked questions
Where is Jev used?
In the approval review that gates workspace actions, per the list summary.
Can community contributors run it locally?
Only partially; a credential-independent setup is not yet documented.
What is opencompany?
An AI workspace with chat, tasks, workflows, integrations, a wiki and cloud coding.
Related projects
Mac app with AI bots running business ops on cloud computers, using TypeSafe for small yes/no calls like risk and which bot takes a job.
ProjectproductionLanguage and VM for long-running agent programs that pause for approval, resume after restarts and replay, with typed decision cells.
ProjectresearchTypeScriptNatural-language CLI where Jev picks which installed 'reflex' programs a sentence calls, running them only when sure enough.
CLIbetaTypeScriptUnix CLI for typed semantic decisions in pipelines and CI: Jev predicates, routes, scores and filters with predictable exit codes.
CLIbetaPythonNative macOS agent app wiring 23 LLM providers into a task loop, listed with an optional Jev command-risk advisor via a TypeSafeKit client.
LibraryproductionSwiftx402 pre-payment risk-check provider combining sanctions lists, phishing feeds and simulation with Jev checks for injected instructions.
Projectproduction