Agent wiki and visual workspace for Claude Code, Codex and other AI coding agents
Stage
MVP
Not given
Founded
Not given
Not given
Based in
US
Not given
Pricing model
Contact for pricing
Freemium
Pricing
Per-execution pricing: one fee per execution that returns proof, charged only when proof comes back. Failed or cancelled runs cost nothing. Planning and approvals are free.
Free: Nimbalyst app and personal wiki. Wiki Teams: $20 per user per month or $200 per user per year (currently free during beta).
Key features
Boundary approval system for controlled execution
Checkpoint-based resumable execution
Verifiable proof of completion
Composable proof for multi-agent workflows
Per-execution pricing model
Integration with multiple agent frameworks
WYSIWYG markdown editor with AI-assisted editing
Red/green inline diffs for AI changes approval
Visual editors for mockups, diagrams, and drawings
Parallel agent session management
File and session linking
Persistent searchable session history
Pull request review in Developer Mode
MCP server support
What makes it different
Pay only for verified results, not for attempts or planning
Human-approved boundaries ensure agent actions stay within limits
Interruptible checkpoints allow pausing and resuming executions
Proof is built into results for auditability and composability
Agents write the wiki as they work, eliminating manual documentation
Open source and local-first: your data stays on your machine
Built by Evergage founders who scaled to $250M ARR
One unified workspace instead of multiple disconnected tools
Kairos
Nimbalyst