Organization repository on GitHub
Universal local System One decision service & daemon supporting Laya, Ollama, and OpenAI-compatible models
- Forks
- 0
- Last pushed
- Updated Sep 2026
Repo stats from the GitHub API, cached Oct 2026.
Jev directory
CommunityJev Agents & MCP
Local Systemone
A lightweight self-hosted System 1 decision daemon and MCP server for AI agents and multi-agent swarms: it evaluates state text against typed choice, score and noul questions in one forward pass, with Laya, Ollama and OpenAI-compatible backends.
- Stars
- 0
- Language
- Python
- Reading time
- 2 min
- Published by
- Community
- Author
- axiomantic
- Last verified
- Oct 2026
Used inJev for Software & DevTools
- Languages
- Python
- Capabilities
- Open sourceSelf-hostedRuns locally
Highlights
- Exposes a Jev-compatible POST /v1/systemone endpoint with pluggable backends, defaulting to Laya's ModernBERT models.
- Latency table: Laya about 25-45 ms on Apple Silicon MPS, CUDA or CPU; Ollama roughly 150-400 ms.
- Evaluates state text against typed choice, score and noul schemas in one forward pass, returning calibrated probabilities.
- Built for AI agents and multi-agent swarms such as Rhizo and Garden, and for orchestration loops.
- Python from axiomantic; 0 stars, created and pushed 2026-09-30, no license listed in the digest.
Watch out
README and GitHub metadata reviewed 2026-10-17; the captured text breaks off inside the backend table, mid OpenAI/llamacpp row, so authentication, the MCP tool surface, setup steps and any benchmarks are not visible, and no license is listed.
Questions about this entry
Short answers drawn from the linked project or page.
A lightweight self-hosted decision daemon and MCP server that gives AI agents and orchestration loops System 1 typed decisions instead of generated text.
It exposes the standard Jev-compatible POST /v1/systemone endpoint and answers the same typed question schemas—choice, score and noul—in a single forward pass with calibrated probabilities.
Laya is the default, running ModernBERT-large at 421M and mmBERT-base at 322M parameters; Ollama and OpenAI/llamacpp-compatible servers can be selected with engine flags or environment variables.
The README's table gives roughly 25-45 ms for the Laya backend on Apple Silicon Metal, CUDA or CPU with RLCD calibration, and about 150-400 ms when routing through a local Ollama instance.
AI agents and multi-agent swarms such as Rhizo and Garden, plus orchestration loops; the README argues a typed decision beats parsing an autoregressive model's generated output.
The Laya backend runs on Apple Silicon Metal, CUDA or CPU, so a GPU is not required; memory figures are not in the captured excerpt, and no license is listed.
It is a Python repository by axiomantic with 0 stars and 0 forks, created and last pushed 2026-09-30; the captured README stops inside the backend table, so setup and MCP details are unavailable.
Reactions & coverage
Posts, threads, and videos about this entry from around the web.
X: Jev in front of the HeyGen MCP
X: Playwright CLI + Jev vs Playwright MCP
X: A local MCP server that cuts computer use from 23s to 0.8s. Cartwright built Cortex, a local MCP server where…
X: A side panel that drives any site's WebMCP tools
More Jev resources like this
A plugin-based agent harness (FastAPI + Vue 3) bundling a chat GUI, multi-provider model access, an MCP client and marketplace, skills, workflow studio, sandboxed execution and a Tauri desktop shell. It integrates TypeSafe AI's Jev for structured Choice, Score and Noul decisions.
Jev Agents & MCP#community#github#agents
Community
andyqiuqiubo/andy-harnessTypeScript
andyqiuqiubo/andy-harnessTypeScriptA 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/snapdecPythonA dependency-free MCP server that exposes TypeSafe's Jev to Claude Code, Codex, Cursor, Hermes, and other agents through the ask_jev and list_jev_models tools, so your code gets typed decisions with probabilities instead of prose to parse.
Jev Agents & MCP#community#catalog-import#logicrw
Community
codeia-academy/jev-mcpPython
codeia-academy/jev-mcpPythonAn open-source Jev-based MCP router: it discovers, catalogs, classifies and deduplicates every MCP server and tool you have, then exposes each agent only the small, authorized subset it needs for the task. Routing decisions are System One Choice/Score/Noul questions, scored by a pluggable engine at the edge or hosted.
Jev Agents & MCP#community#catalog-import#logicrw
Community
amantux/mcp-routerPython
amantux/mcp-routerPythonA local daemon that pulls open decision models and serves them on TypeSafe's /v1/systemone, so a Jev client switches hosts with TYPESAFE_BASE_URL.
Jev Models & Reimplementations#community#rust#open-models
Community
ollaya-dev/ollayaRust
ollaya-dev/ollayaRustHTTP server for the Mica v0.5 4B Preview decision model: GGUF weights run through llama.cpp and answer noul, choice and score questions with calibrated probabilities over the TypeSafe /v1/systemone format.
Jev Repos & SDKs#community#github#python
Community
akivet/MicaPython
akivet/MicaPythonFrom 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.