General work
Coordinate work that does not need a specialist template.
Jentra coordinates people and agents from a shared direction to a verified result. Start with the route that matches your work, then go deeper only when you need to.
Follow this route for a first real Project. You can use hosted Jentra, Local Docker or your own Cloudflare account. Jentra coordinates the work; your connected model or agent performs it.
Use the hosted experiment for the quickest start, Local Docker for private evaluation, or your own Cloudflare account for an always-reachable installation.
Sign up, follow the email verification link when hosted, sign in and complete onboarding. Local Docker keeps accounts local and does not require email verification.
Use a Project as the durable home for related source, participants, work, memory and policy.
State what should be true when the work is finished, what must not change and how the result should be checked. The first prompt is initial intent, not an irreversible final goal.
Use Direct for exploration, Quick Task for one bounded change, or Managed Journey for consequential, parallel or long-running work.
Import a Git repository, use an existing compatible remote, bring files, or start empty. Private imports remain blocked until an approved runtime can resolve the credential reference.
Use a compatible IDE, CLI, runtime host, MCP connection or agent harness. Jentra does not bundle a model or silently charge for one.
Choose what agents may do autonomously, which tools they may use and which delivery, spending or policy boundaries still require a person.
Jentra gives each Assignment its objective, relevant context, capability envelope and isolated or deliberately collaborative World.
Use activity, attention, checkpoints and Ask why to understand progress without watching every model message.
Inspect the result, provenance, claims, evidence, known limitations and unresolved questions.
Run proportionate checks. Independent verification must come from an eligible participant other than the work author.
Compose accepted work, then merge, publish or deploy only through a separately authorised action. Keep, archive or clean up Worlds according to the Project policy.
Create a small reading-list app with add, complete, filter and local persistence. Give implementation to one agent and verification to another. This exercises source, Worlds, context, evidence and handoff without wasting model usage.
Not every action needs a Journey. Jentra adds structure in proportion to consequence and coordination.
Jentra may require a Managed Journey when work has multiple participants, dependencies, high risk, mandatory independent verification or a reserved human decision.
Choose the closest work kind during onboarding. It changes the language and suggested checks, while the same coordination model keeps direction, authority, evidence and decisions connected.
Coordinate work that does not need a specialist template.
Frame direction as a product change, acceptance checks and technical boundaries.
Frame direction as a question, investigation, evidence standard and research boundaries.
Frame direction around an audience change, campaign outcome, success signals and boundaries.
Frame direction as a desired state, operational checks and safeguards.
Frame direction as a deliverable, review standard and creative boundaries.
The work kind can change as the Project evolves. It does not restrict compatible agents, tools or outputs, and older Journeys remain valid as General work.
These routes take you directly to the relevant instructions. Start with the end-to-end route when you are unsure.
A Journey carries consequential work from shared direction to a verified result. It remains understandable even when participants change.
The shared direction, policy, current state, accepted context and final resolution.
A bounded part of the current direction with a role, capability envelope, completion criteria and dependencies.
One execution attempt by an agent or runtime. A retry is a new attempt, not rewritten history.
A proposed result with author, source, claims, changes and attached evidence.
Each assigned agent receives a versioned handoff containing the Journey direction, its role, current accepted context, relevant prior results, dependencies, boundaries and remaining work. Consequential callbacks bind to an alignment hash; stale agents must refresh before continuing.
Projects learn as they move. The first prompt records initial intent, but it may not remain the final direction.
Jentra records each accepted Direction revision, assesses affected work and requires stale agents to refresh their alignment envelope before consequential results can change canonical state.
Stop new consequential results from being accepted against the old direction.
Capture the new direction, why it changed and the evidence or decision behind it.
Keep unaffected Assignments. Replace, revise or supersede anything that no longer serves the current result.
Issue new Assignment context before work resumes. Treat incompatible earlier results as historical evidence, not current deliverables.
For a small change, revise the bounded Assignment. For a change that alters the purpose of the work, begin a new Managed Journey inside the same Project so the earlier history remains intact.
Jentra is compatible with different agent harnesses. It coordinates authority and shared state; the connected harness executes the work.
Agents may work end to end within the permissions, time, tools and spending boundaries you choose. Human approval is not required at every step.
Jentra pauses when policy reserves a consequential choice, a capability must widen, or a sensitive delivery action needs approval.
A World may contain a lead agent and bounded subordinate groups. The lead coordinates local work while the Journey remains the canonical authority.
Codex, Hermes, Claude Code and other compatible hosts may retain their own skills and private runtime memory. Jentra does not assume identical harness internals.
Journey participants can message agents, reply in context and propose a change from the same conversation. Ordinary coordination is recorded immediately. A consequential proposal remains pending until an authorised person applies it through Direction, Assignment, Assurance or Decision workflow. A chat message never silently changes canonical state.
Open Agent operations inside a Managed Journey to see responsibility, current execution, alignment, recovery and authority without reading every model message.
Jentra surfaces blocking attention, stale alignment, failed or unresponsive Runs and unavailable capacity. Routine activity remains in the Journey timeline.
A World is an isolated or deliberately collaborative workspace for an Assignment. For code, it is backed by ordinary Git concepts.
For research, marketing and document work, a World can expose the files and tools needed by the agent. The same boundaries apply: scoped access, evidence, attribution and explicit delivery.
Jentra separates “work completed” from “result trusted.”
Jentra keeps current work aligned and can recall approved knowledge without turning every transcript into permanent memory.
Private to your account by default. You can inspect, correct, forget, purge and export it.
Shared only after an explicit promotion and authorised review. Retraction remains auditable.
Agents receive the relevant direction, role, constraints, decisions, evidence and remaining work, not an unbounded transcript dump.
Jentra does not copy hidden reasoning, credentials, private agent memory or provider checkpoints into shared context.
Hosted Jentra is capped to prevent unexpected cost and abuse. Limits are configuration, not permanent product assumptions.
Open Project > Agent setup. Add a provider or runtime, enter only the secret alias held by that runtime, then assign its models to work, decision, verification or fallback roles. One connection can serve multiple agents. Jentra never asks for the raw key, and your provider or runtime still controls billing, rate limits and concurrency.
Portable setup profiles describe what an Assignment needs without copying credentials or private state.
Add a versioned profile that names model roles, skills, MCP servers and required capabilities.
A Project owner approves the exact revision and content hash. Importing never starts work or installs software.
The harness reports its inventory. Jentra identifies missing requirements, incompatibility and version drift before launch.
Use a Project default or an approved Journey- or Assignment-specific profile. The most specific binding wins.
Model roles include WORK, DECISION_ADVISER, INDEPENDENT_VERIFIER and FALLBACK. A model role configures execution; it does not grant authority.
npx -y @jentra/mcp-serverSet JENTRA_API_URL and a scoped JENTRA_SESSION_TOKEN in your harness secret configuration. The stdio server exposes Project context, Assignment context, Change Review, People & Agents and canonical command submission.
npm pack @jentra/agent-skillExtract the archive and point your harness at SKILL.md, or copy it into the harness's supported skill directory. The skill contains behaviour and safety guidance only; live state always comes from Jentra.
The CLI is useful from a terminal, IDE task or agent harness.
npm install --global @jentra/cli
jentra --versionSet JENTRA_API_URL to the control-plane origin and provide a Better Auth bearer session using JENTRA_SESSION_TOKEN. Keep tokens in your shell or secret manager, never in source control.
jentra journey <journey-id> --jsonRead the canonical Journey snapshot.jentra capsule export <journey-id> --output journey-capsule.jsonExport the current portable continuation package.jentra capsule verify ./journey-capsule.jsonVerify the Capsule and its instruction hashes before continuing elsewhere.jentra why <journey-id> <commit-or-ref>Inspect provenance for a result.jentra attention <journey-id>See what needs action.jentra assurance <journey-id>Inspect verification state.jentra memory list --jsonList your private memories.Machine-readable errors include a code, message, retry class, remediation actions and correlation ID.
Local and self-hosted users can run project-defined build, test, lint, type-check and policy commands on their own machine. Cloudflare and hosted CI are not required.
Inspect jentra.checks.json. Commands use an executable and argument array, not a shell string. Independent commands may run concurrently and dependsOn defines ordering.
Supply the exact commit, tree or content hash being checked.
Use jentra check local --candidate <hash>. Use jentra check init-ci --provider github or gitlab to create a reviewable starting workflow.
Add --journey <id> --direction <revision-id> --upload when the result should appear in Change Review. Declared artifact files are bounded and represented by digest.
A passing Check does not independently verify, accept, merge, publish or deploy work. It becomes stale when its candidate, dependencies or accepted Direction change.
The direct runner terminates process trees on cancellation or timeout. Use a sandboxed eligible runner when network or stronger resource isolation is mandatory. The basic local runner fails closed when such isolation is required.
Use the public contracts, TypeScript SDK and HTTP API to build compatible clients and automation.
Projects and activity previews; Journeys and Assignments; participants and Worlds; contributions and verification; decisions and resolution; runtime placement and callbacks; setup profiles; memory and usage.
Use exported schemas rather than guessing request fields. Treat structured remediation as part of the error contract.
A runtime host turns Jentra Assignments into work performed by Codex, Hermes or another compatible harness.
Advertise a reachable host, adapter, capabilities, capacity and an opaque authorisation reference.
Validate the Assignment, World, capability grant, exact instruction package, alignment envelope, expiry and idempotency key.
Resolve credentials from the host secret store and run inside the assigned World.
Send ordered heartbeats, checkpoints and one terminal result. Duplicate callbacks are safe; conflicting replays fail closed.
Compatible hosts must recover accepted work durably, honour cancellation, enforce capacity and refuse stale or capability-incompatible work. New hosts can advertise Jentra native-tool vocabulary versions, tool versions and bounded actions so Assignments remain portable across providers without assuming that two similarly named tools behave the same.
Signed-in users can open Runtime connections to see heartbeat freshness, available execution slots, advertised capabilities and native tools, checkpoint support and the exact reason a runtime does not match an adapter, capability or tool requirement. Secret values and runtime endpoints are not shown.
A verified Journey Capsule can hand active work from one compatible harness or location to another. It carries bounded Assignments, current Direction, authority and integrity hashes. Export fails safely if an active Assignment has not been dispatched against the current Direction. Refresh or restart that Assignment, export again, then verify the Capsule before continuing and recording a handoff receipt.
Use the public SDK, CLI, MCP server and agent skill with an Apache-2.0 coordination backend. The private hosted control plane is not required.
npx @jentra/community-runtime init
npx @jentra/community-runtime start, then open http://127.0.0.1:4317. Create a Project, start work and connect an existing local Git repository.
Create an isolated World backed by a real Git worktree. Commit there, propose the current commit and record an explicit accept or reject decision in Change Review.
Set JENTRA_API_URL=http://127.0.0.1:4317 and a local participant identity, then launch npx @jentra/mcp-server. Agents read the same direction, Worlds, coordination messages and review state shown in the browser.
The Community Runtime includes local Projects, Journeys, Git-backed Worlds, participants, shared coordination messages, current direction, append-only activity, versioned commands and contribution review. It does not silently merge or deploy. Managed execution, hosted identity, billing and large-scale scheduling remain outside this edition.
Read the source and contribute
The runtime binds to loopback and writes .jentra/community.json. Existing repository state remains intact when a connection or replacement fails. Set a strong bearer token before exposing the runtime to another interface, and never store secret values in Journey context.
Run the Jentra control plane without depending on the hosted service.
The experimental self-hosted package contains the Jentra control plane, not a bundled model or agent. Your installation owns its accounts, coordination data, evidence and connected-provider credentials.
For private evaluation, solo work or a small trusted team. Runs on one computer and requires no Cloudflare account.
For an always-reachable Control Room using infrastructure you own.
The current bundle passed package verification and a clean Local Docker installation. Accept the experimental self-hosted licence, then download it directly; no email or access request required.
Download self-hosted previewJentra separates account identity, agent execution and provider credentials.
Start with the symptom you can see. Jentra should preserve accepted state when an external service or runtime fails.
BETTER_AUTH_URL and BETTER_AUTH_TRUSTED_ORIGINS.npm run verify, confirm Docker Compose v2 is available, inspect npm run local:logs and keep the generated .env secret with the existing data volume.BETTER_AUTH_SECRET is set. Then redeploy without deleting user-owned data.Record the Jentra version, installation method, operating system, integration, reproduction steps, visible correlation ID and sanitised logs. Never include API keys, access tokens, private repository content, Journey data or unsanitised artifacts.
Jentra will recommend the lightest route that keeps the work understandable.
Try a broader term, or clear the search to browse the full documentation.