Live
Memory and recall
Agent Brain
Self-hosted shared memory, semantic cache, and governance for Claude, Codex, Cursor, Gemini, Aider, and custom agents.
Four core products.One connected development loop.
Each core product exists because a different part of the workflow kept breaking down in practice: context drift, lost notes, messy multi-agent runs, or a terminal that was never built for this style of development in the first place.
Studio and Avatar are separate internal projects in development, currently used to produce the suite's marketing material. They are not available products or services.
Live
Voice capture
Agent Wispr
Voice-first capture for agentic development notes, prompts, decisions, and task handoffs.
Live
Agent orchestration
Agent Harness
AI agent execution harness with local models, verification, approvals, routing, and recovery.
Live
Developer terminal
Agent Terminal
Voice-to-agent developer terminal. Speak a goal, enrich with Brain memory, run the pre-send guard, and delegate to Harness workers — from one native desktop app. Log in once and stay signed in across the full suite.
Coming soon
Launch video studio
Agent Studio
Internal project in development used to produce the suite's launch material. The done-for-you SaaS launch-video service is not currently available.
Coming soon
Voice and video cloning
Agent Avatar
Internal project in development used to produce the suite's presenter and voice material. The local voice-and-video product is not currently available.
Release status
Agent Brain
LiveSelf-hosted shared memory, semantic cache, and governance for Claude, Codex, Cursor, Gemini, Aider, and custom agents.
Public site, docs surface, or offer page is already live and usable now.
Agent Wispr
LiveVoice-first capture for agentic development notes, prompts, decisions, and task handoffs.
Public site, docs surface, or offer page is already live and usable now.
Agent Harness
LiveAI agent execution harness with local models, verification, approvals, routing, and recovery.
Public site, docs surface, or offer page is already live and usable now.
Agent Terminal
LiveVoice-to-agent developer terminal. Speak a goal, enrich with Brain memory, run the pre-send guard, and delegate to Harness workers — from one native desktop app. Log in once and stay signed in across the full suite.
Public site, docs surface, or offer page is already live and usable now.
Agent Studio
Coming soonInternal project in development used to produce the suite's launch material. The done-for-you SaaS launch-video service is not currently available.
Agent Avatar
Coming soonInternal project in development used to produce the suite's presenter and voice material. The local voice-and-video product is not currently available.
How the suite fits together
Agent Wispr
Capture intent without breaking flow
Speak a bug report, implementation idea, decision, or task handoff. Wispr turns it into usable text locally so the thought can move straight into the development loop instead of getting lost in a scratchpad.
Agent Brain
Recall the context that makes the request useful
Brain searches durable project memory, semantic cache entries, and learned execution patterns, then gives Terminal and connected agents the relevant context without stuffing every past session into the prompt.
Agent Harness
Run bounded work with evidence
Harness routes a focused task to a worker, keeps the scope and expected result explicit, applies policy, runs verification, and reports the run status instead of treating a worker's confidence as proof.
Agent Terminal
Keep the operator in control
Terminal is the bridge: it receives the composer draft, asks Brain for reusable answers and rewrite suggestions, runs the pre-send guard, launches bounded Harness work, tracks the result, and writes useful execution outcomes back to Brain.