local AI operations console

hecate

Run Hecate on your machine between AI clients, model providers, coding agents, and workspace tools so project work can be coordinated, routed, approved, traced, and reviewable.

Download for macOS Other platforms View source

v0.1.0-alpha.45 · release notes · all releases · GitHub

public alpha

Install the local console.

macOS Apple Silicon Download .dmg Linux x86_64 Download .AppImage Windows x86_64 Download .msi

project workflow

Project work gets a durable local identity.

Start with a project, attach workspace roots when files matter, and keep chats, tasks, external-agent sessions, context, memory, and evidence connected to the same work.

Model gateway Route OpenAI-compatible and Anthropic-shaped requests across cloud and local providers with health, failover, and usage visibility.

Project orchestration Coordinate durable projects, workspace roots, assignments, handoffs, context snapshots, and operator-approved memory.

External agents Supervise local Codex, Claude Code, Cursor, and Grok Build sessions while their CLIs keep their own accounts and runtimes.

Evidence Keep traces, route reports, task artifacts, diffs, logs, usage, and final output close to the decision that produced them.

Hecate chat screen with an approval required before a file write

operator control

Agents wait before crossing the line.

Hecate keeps file writes, tool actions, approvals, artifacts, and run context visible before supervised work changes the workspace.

observability

Route reports and traces are first-class.

Hecate is OpenTelemetry-first: requests surface trace IDs, route decisions, timing, token usage, and provider-reported cost where available.

Hecate observability screen with recent requests and spans

hosted direction

Open source first. Hosted runtimes stay separate.

hecate.sh stays focused on the open-source local console. Hecate Cloud will live separately at hecatehq.com, with the console at console.hecatehq.com.

Hecate Cloud