User repository on GitHub
Snap decisions for coding agents — one command, any machine, any agent. Local System One decision layer (MCP + Agent Skill).
- Forks
- 1
- Last pushed
- Updated Oct 2026
Repo stats from the GitHub API, cached Oct 2026.
Jev directory
CommunityJev Agents & MCP
Snapdec
A 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.
- Stars
- 2
- Language
- Python
- License
- APACHE-2.0
- Reading time
- 2 min
- Published by
- Community
- Author
- aktonay
- Last verified
- Oct 2026
- Languages
- Python
- Capabilities
- Open sourceRuns locally
Highlights
- A local System One decision layer for AI coding agents, described as one command for any machine and any agent.
- Offloads high-volume classification, checks, scores and ranking from frontier LLMs to sub-50ms local models.
- Ships as an MCP server plus an Agent Skill; listed in the MCP registry and published on PyPI as snapdec.
- Advertises macOS, Linux and Windows support; Apache-2.0 with CI on GitHub Actions.
Watch out
README and GitHub metadata reviewed 2026-10-17; the digest cuts off at the README banner, so the install command, the local models it runs and its measured latency distributions are not evidenced here.
Questions about this entry
Short answers drawn from the linked project or page.
snapdec is a local System One decision layer for AI coding agents, delivered as an MCP server and Agent Skill, that moves high-volume classification, checks, scores and ranking off frontier LLMs.
The README banner promises fast, calibrated micro-decisions by offloading them to sub-50ms local models. The digest cuts off at the banner, so the models involved and measured latency distributions are not evidenced.
It is described as a local System One decision layer, using the typed, calibrated decision pattern associated with Jev but running locally. The digest does not state whether it calls Jev or a different model server.
The digest truncates the README at the banner image, so no install command is shown. The project is published on PyPI as snapdec and listed in the MCP registry, per the README badges.
The README badges list macOS, Linux and Windows. The digest excerpt does not document per-platform limitations, hardware requirements or model download sizes.
The banner names classification, checks, scores and ranking as the micro-decisions it offloads from frontier LLMs. The digest does not show the tool schemas, prompts or example outputs.
The aktonay GitHub account, under Apache-2.0, with 2 stars and 1 fork; created 2026-10-03 and last pushed 2026-10-11. CI runs through GitHub Actions.
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 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.
Jev Agents & MCP#community#github#mcp
Community
axiomantic/local-systemonePython
axiomantic/local-systemonePythonLocal-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_memoryPythonDjaevin, a calibrated, local-first decision layer from Icaro0310 that runs behind a Devin ACP backend with no API key. It ships as an MCP server published in the official MCP Registry and installs from PyPI as poordjaevin; the repo topics name calibration, conformal prediction and NLI.
Jev Agents & MCP#community#github#python
Community
icaro0310/devin-judgePython
icaro0310/devin-judgePythonA 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 MCP server and CLI web crawler for AI agents in which a small decision model picks every link and passage, so the agent's LLM reads only what answers its question. On 50 WebWalkerQA tasks the README claims 40% correct answers at about $0.025 per task.
Jev Agents & MCP#community#github#python
Community
rayenmlayeh/jevcrawlPython
rayenmlayeh/jevcrawlPythonA zero-embedding approach to video intelligence from DeepAleph: jevreel lays a video out on labelled contact sheets, one frame per second and sixty frames to an image, and has Jev judge every sheet in parallel. Your coding agent gets moments, times and probabilities back over MCP.
Jev Agents & MCP#community#github#mcp
Community
deepaleph/jevreelPython
deepaleph/jevreelPythonFrom 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.