Private work agent for overloaded teams

Your inbox is not the source of truth. Echelon is.

Echelon reads the work streams you already live in, groups related activity into durable cards, drafts the next move and waits for your approval before anything leaves your machine.

today / owner queue
Slack · GitHub · Jira

Release blocker grouped into one card

Three threads and one pull request describe the same issue. Echelon keeps the context together and suggests the next reply.

Teams

Needs your decision

Client asked for a deployment date. No message will be sent until you choose one.

Notion

Meeting note converted into actions

Two owners found, one follow-up drafted, no noise added to the board.

SlackTeamsGitHubJiraNotionLocal files

How it works

One quiet loop instead of another dashboard.

01

Collect

Connectors read messages, issues, pull requests and notes into a local event log.

02

Understand

Related conversations become one work card, with the owner’s replies kept in the timeline.

03

Propose

The agent drafts replies, next steps and handovers with citations to the source material.

04

Wait

The queue asks for approval. Sending, rejecting and changing policy stay human decisions.

Built for control, not autopilot.

Echelon is local-first. Credentials stay in the OS keychain. Drafts queue for approval. Automation is scoped by policy, per platform and per recipient.

No cloud telemetry by default.

Every outbound message passes through a send gate.

Model providers are modular: Claude Code, API keys, local models or ChatGPT Codex.

Now in private build

For operators who need memory, drafts and decisions in one place.

Talk to us