lichen — Local Jev Alternative

ollaya downloads named open decision models and serves typed questions through a local daemon. It implements TypeSafe-compatible endpoints for existing Jev clients, while remaining an independent project. Use its CLI, desktop app or MCP server; Modelfiles can package reusable question sets.

Simple Jev uses compatible Hugging Face models to classify and score inputs, constructing JSON answers from next-token logits instead of generating a completion. Send shared context as either state or messages, plus typed questions, to POST /v1/classifier on the configured server.

OpenJev reads typed answers from open-model probabilities and serves choices, scores and yes/no judgments, including image questions for its main model. Point the TypeSafe SDK’s base URL at your server or the documented hosted endpoint, then call system_one with state and questions.

jeff serves a Jev-compatible System One API using GLiFormer weights for Choice, Score and Noul decisions. Use Python 3.12 and uv, download the checkpoint, set JEFF_API_KEYS and point the client at localhost:8000.

Supersimple way to serve LLMs as a Jev-like endpoint

A tiny jev-like model that answers Choice, Score and Noul questions in one forward pass and returns calibrated probabilities. MLX or PyTorch, fully offline, System One compatible.

Instructions, tools, skills, channels and schedules live in conventional directories, making an agent project inspectable and extensible. The evaluate helper sends typed questions about supplied state through eve's model authentication, defaulting to Jev.

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.