PerryLink1051Updated 3d ago
TypeSafe Jev for DeepSeek Harness, the Model Context Protocol, and plain Node: typed judgments instead of prose, offline by default.
Practical score
78 / 100
Setup
Needs setup
License
Apache-2.0
Language
TypeScript
Copy the command, or hand the whole task to your harness agent.
git clone https://github.com/PerryLink/jevcore.gitPlease install the DeepSeek Harness plugin "jevcore" for me. - GitHub repository: PerryLink/jevcore (https://github.com/PerryLink/jevcore) - Type: a Cordis plugin (installed into a DSH profile) - The plugin declares a DSH version requirement of 0.1.6-alpha.2.…
A cleaned excerpt from the project's own documentation.
jevcore TypeSafe Jev for DeepSeek Harness and any other MCP host. Jev is not a chat model. It answers typed questions — noul (yes/no), choice , score — and returns calibrated probabilities. It does not write prose, and asking it to is a category error. This project gives an agent exactly that surface, and nothing more. Offline by default. Egress disclosed. Nothing default-on. --- 📖 Ecosystem knowledge base — measured data, not marketing:…
Open on GitHubSimilar tools from the same corner of the ecosystem.
PerryLink
MCP management console for the official DSH MCP client: server CRUD with approval-gated, backed-up profile writes, a tool trial console through the official tool pipeline, health diagnostics, and connection status.
JerryLiu369
Agent-native multi-provider web search for AI agents (Claude Code, Hermes, DeepSeek Harness, OpenCode, Codex). Model grounding (Responses, ARK) + semantic search (Exa, Parallel) + keyless defaults via MCP, CLI, and DSH plugin.
PerryLink
Second-model AI auto-review on the approval answerer chain: a read-only reviewer subagent returns structured allow/deny verdicts with reasons, fail-closed by default.