eve: filesystem agents with Jev evaluation

Developers define allowed components and actions so generated interfaces follow their own catalog and schema. The playground's experimental composer uses typesafe-ai/jev to evaluate candidate components while building a UI specification.

OpenInference supplies conventions and instrumentation for tracing AI applications, including model calls, retrieval and external tools. Its TypeSafe integration records systemOne calls as spans with JSON inputs and outputs, model and token usage; examples cover Choice, Noul and Score.

Jev MCP gives agents tools for evidence verification, classification, reranking, extraction and patch review. Register npx -y @jkudish/jev-mcp in an MCP client using Node.js 22 or newer and a configured Jev provider key.

Web Search Plus adds web search and page extraction tools to Hermes, with routing and fallback across configured providers. Install the Hermes plugin and configure a search provider. Enable Jev separately with setup --jev and install typesafe-sdk.

pg-jev filters, ranks and classifies PostgreSQL rows using plain-language SQL conditions. Batched Jev questions judge rows; SQL functions expose boolean, probability, choice and rubric-score results. Requires PostgreSQL 14–17, plpython3u, superuser access and a TypeSafe key.

The plugin uses Jev to recommend available tools, skills and task owners and to evaluate output against defined criteria. Install the native DSH bundle or import the iPolloWork package, configure a TypeSafe key, then check status before a live connection test.

The native CLI supports an interactive shell, scripted requests and embedding, with skills, MCP servers and subagents. Jev receives review policy, context and the pending action, returning a clear or caution decision for the permission pipeline.

The platform supports developing and evaluating SRE agents against live system environments containing operational failure scenarios. Jev support is disabled by default; when enabled for Codex, it reviews diagnostic tests and submissions from evidence sent to TypeSafe.

No project description available.

🚀 Feather Wand - JMeter Agent for performance engineers w/ Codex and Claude Code integration

Agent orchestration that guides projects toward demonstrable goals.

Self-hostable managed agents harness. Author YAML manifests; Felix compiles them into governed agents with durable fibers, memory, skills, eval, approvals, and sandboxes — over OpenAI, A2A, MCP, and SSE. Fork, rewind, and steer runs. Docker, Helm, AWS, or GCP.