User repository on GitHub
- Forks
- 0
- Last pushed
- Updated Oct 2026
Repo stats from the GitHub API, cached Oct 2026.
Jev directory
CommunityJev Agents & MCP
systemone Sidecar by vstaln
A sidecar plugin that puts fast typed-decision models such as TypeSafe Jev and Laya behind two tools over one wire format (POST /v1/systemone): judge asks typed questions about a state and returns probabilities, while semantic_find scores file chunks against a plain-language query.
- Stars
- 0
- Language
- Rust
- License
- MIT
- Reading time
- 2 min
- Published by
- Community
- Author
- vstaln
- Last verified
- Oct 2026
Used inJev for Software & DevTools
- Languages
- Rust
- Capabilities
- Open sourceRuns locally
Highlights
- Every backend speaks the same wire format, POST base/v1/systemone, so one client with a configurable base URL covers TypeSafe Jev, Laya and other open models.
- Two tools: judge asks typed questions about a state and returns probabilities, not prose; semantic_find scores file chunks for meanings keyword grep misses.
- A /s1 command reports status and runs a one-shot yes/no check from chat.
- Defaults: base URL http://localhost:11435 with a local Ollaya daemon serving laya; elsewhere the model defaults to jev-latest.
- Configuration is environment-only: SYSTEMONE_BASE_URL, SYSTEMONE_MODEL and SYSTEMONE_API_KEY, falling back to TYPESAFE_BASE_URL and TYPESAFE_API_KEY.
Quickstart
bash
curl -fsSL https://ollaya.dev/install.sh | sh
ollaya pull laya
ollaya serveWatch out
README reviewed 2026-10-17; the captured text cuts off inside the backends table, so host-application setup, install steps and error behavior are not documented, and the repo has 0 stars.
Questions about this entry
Short answers drawn from the linked project or page.
A sidecar plugin that puts fast typed-decision models such as TypeSafe Jev and Laya behind two tools, judge and semantic_find, plus a /s1 status check.
Ollaya (local, the default), TypeSafe, and any server speaking the same POST /v1/systemone wire format, which lets one client cover all of them with a configurable base URL.
Environment variables only: SYSTEMONE_BASE_URL, SYSTEMONE_MODEL and SYSTEMONE_API_KEY, with fallbacks to TYPESAFE_BASE_URL and TYPESAFE_API_KEY.
It asks typed questions about a state and returns probabilities, not prose, so callers get calibrated answers to narrow questions.
The decision model scores file chunks against a plain-language query, finding meaning-based matches when keyword grep is not enough.
Install Ollaya with its install script, then run ollaya pull laya and ollaya serve; the daemon listens on port 11435.
laya when the backend is localhost, otherwise jev-latest, overridable through the SYSTEMONE_MODEL environment variable.
More Jev resources like this
A Rust MCP server that recommends third-party agent skills: it retrieves deduplicated metadata with SQLite FTS5/BM25, sends one comparable typed Score per candidate in batches of at most 128 questions, and never installs or executes a skill.
Jev Agents & MCP#community#github#mcp
Community
king4s/jev-skill-routerPython
king4s/jev-skill-routerPythonLocal code search for coding agents: ripgrep and BM25 shortlist function-level chunks, Jev Noul relevance questions run across parallel requests, and accepted excerpts return to Codex, Claude Code, OpenCode or Pi through MCP or the `oko ask` command.
Jev Agents & MCP#community#mcp#code-search
Community
bartlomein/okoRust
bartlomein/okoRustA Rust harness for desktop and browser automation where every choice about what to press comes from Jev: the decision model answers small closed questions about the screen while plain Rust reads the screen as named buttons and fields, acts, verifies and enforces the safety rules. It stops before money moves.
Jev Agents & MCP#community#github#rust
Community
tinyhumansai/tinycomputerRust
tinyhumansai/tinycomputerRustA local System One decision layer for AI coding agents, shipped as an MCP server and Agent Skill, that offloads high-volume classification, checks, scores and ranking from frontier LLMs to sub-50ms local models with calibrated output.
Jev Agents & MCP#community#github#mcp
Community
aktonay/snapdecPython
aktonay/snapdecPythonLocal-first MCP memory server for IDEs: tree-sitter indexing into a local ChromaDB store, plus an optional Jev layer that screens retrieved passages for relevance, evidence, contradiction and prompt injection.
Jev Agents & MCP#community#github#python
Community
KikeVen/zerikai_memoryPython
KikeVen/zerikai_memoryPythonA memory plugin for the DeepSeek Harness that binds knowledge and handoff documents to projects in one local Markdown directory. Its settings include a decision-model page for JEV-style models over the /v1/systemone protocol, used for active injection and end-of-turn scoring.
Jev Agents & MCP#community#github#javascript
Community
jojoman2024/dsh-memjJavaScript
jojoman2024/dsh-memjJavaScriptFrom the Jev guides
Original write-ups on what this entry is for.
From the Jev AI model community
Posts from builders shipping with Jev right now.