| What it does | The governed AI coding platform
| AI agent observability for Elixir
|
|---|
| Stage | Not given
| MVP
|
|---|
| Founded | Not given
| 2026
|
|---|
| Based in | US
| Not given
|
|---|
| Pricing model | Freemium
| Freemium
|
|---|
| Pricing | Open source: Free download, bring your own inference. Coder: $20/mo (includes $25 monthly credits). Teams: $35/seat/mo (includes $45 monthly credits). Enterprise: Custom pricing. Code Review add-on: $15/user/mo.
| Free: €0/month with 100,000 accepted events/month, 100 MB/hour, 14 days retention, 1 project, 2 users. Pro: €29/month with 1,000,000 accepted events/month, 2.5 GB/hour, 30 days retention, unlimited projects and users. Scale: €99/month with 10,000,000 accepted events/month, 5 GB/hour, 90 days retenti
|
|---|
| Key features | - Multi-model routing automatically orchestrates models by task type and cost
- Hard spending limits enforced by user, team, API key, or model
- Autonomous /ferment workflow breaks tasks into milestones and delivers PRs
- Evaluator grades output against original intent before shipping
- Kimchi Studio visual workspace for watching and guiding parallel agent tasks
- Teleport hands off sessions to persistent cloud sandbox workspaces
- AI-powered code review with inline findings and severity scoring
- VS Code extension brings harness into IDE with governance controls
- One-command migration from Claude Code and OpenCode
- Deploy serverless or in your VPC for full data sovereignty
| - Model and tool call tracing in unified timeline
- Inspect failed steps with inputs and outputs
- Monitor throughput, latency, errors, tokens, and cost
- Single Elixir dependency for instrumentation
- Configurable event filters and analytics
- Shared team visibility across agent runs
- Real-time observation of agent execution
- Configurable data retention by plan
|
|---|
| What makes it different | - One enforcement layer for security, governance and cost controls across all agent requests
- 50+ open-source and open-weight models with zero lock-in
- Data sovereignty by design: prompts, code and outputs excluded from model training
- Real-time cost attribution per developer, team, model and tag
- Get started in 60 seconds with no lock-in or credit card required
| - Purpose-built for Elixir and BEAM applications
- Unified view of model and tool calls with context
- Minimal setup with one dependency and endpoint configuration
- Alerting built on existing tracing and monitoring data
|
|---|
| Community votes | 1 | 0 |
|---|
| DR (Domain Rating by Ahrefs) | 40 ▲ +2 (up) since last check | Not checked yet ● no change since last check |
|---|
| Trust Flow (Majestic) | 14 | 2 |
|---|
| Citation Flow (Majestic) | 33 | 8 |
|---|
| Referring domains (Majestic) | 186 | 35 |
|---|
Kimchi Coding
WeaveScope