User repository on GitHub
System-1 decision model integration, safety governance, and host bridge for Prime Agent
- Forks
- 0
- Last pushed
- Updated Oct 2026
Repo stats from the GitHub API, cached Oct 2026.
Jev directory
CommunityJev Integrations & Adapters
Prime TypeSafe Jev
An MIT-licensed TypeScript bridge that brings System-1 decision models into Prime Agent v0.9.8+ as a decision layer with safety governance and a host bridge. The README advertises 185 passing tests at v0.1.0 and POSIX-only support.
- Stars
- 0
- Language
- TypeScript
- License
- MIT
- Reading time
- 2 min
- Published by
- Community
- Author
- japorto100
- Last verified
- Oct 2026
- Languages
- TypeScript
- Capabilities
- Open source
Highlights
- Brings System-1 decision models into Prime Agent (PrimeIntellect-ai/prime-agent), covering decision integration, safety governance and a host bridge.
- Names TypeSafe JEV and local engines such as capitaharlock/jev-clone, which emit calibrated choice distributions in single-digit milliseconds.
- Badges: 185 tests passing, version v0.1.0, MIT licence, Linux and macOS POSIX only, target Prime Agent v0.9.8+.
- The README adds safety governance because plugging a decision model into an autonomous agent creates hazards such as credential exposure.
Watch out
README reviewed 2026-10-17 from the round-eleven capture, which stops mid-sentence in the Overview while listing operational hazards: install steps, the governance design, compatibility details and any independent latency measurements are not in the digest.
Questions about this entry
Short answers drawn from the linked project or page.
A TypeScript integration that brings System-1 decision models into Prime Agent, adding safety governance and a host bridge. The repository is MIT licensed and currently at version v0.1.0.
An autonomous agent project by PrimeIntellect-ai; this integration targets Prime Agent v0.9.8 or later so the agent can consult a decision model instead of relying only on token generation.
The README names TypeSafe JEV and local engines like capitaharlock/jev-clone — models that take a structured state and emit calibrated distributions over choices in single-digit milliseconds.
The README argues that plugging a decision model directly into an agent creates operational hazards including credential exposure, and says this package adds safety governance and a host bridge to contain them.
v0.1.0 with 185 tests passing per its badge, MIT licensed, and limited to Linux and macOS POSIX systems. The repository has 0 stars and was created 2026-10-14.
Not shown in the digest: the captured README is truncated in the Overview, before any install or configuration instructions, so no commands are reported here.
Everything rests on the README excerpt, which is cut off mid-sentence; latency, governance specifics and test coverage details are unverified, and no benchmark numbers are captured.
More Jev resources like this
A pi agent extension that routes TypeSafe's Jev classifier through OpenRouter to block destructive tool calls, verify test and build output, and rank workspace files for a task. It fails open and costs about $0.00002 per call.
Jev Integrations & Adapters#community#github#typescript
An opencode plugin (also for pi and Claude Code) that puts every bash command in front of a System One decision model before it runs: a small model scores destructiveness, secret leakage, and your repo's GUARDRAILS.md policy and blocks bad calls.
Jev Integrations & Adapters#community#github#opencode
Community
berget-ai/guardrails-mdTypeScript
berget-ai/guardrails-mdTypeScriptAn unofficial Claude Code plugin that checks 'done' claims and small judgement calls with TypeSafe Jev and keeps receipts: its done-gate can reject 'all tests pass' and ask for a real check, so evidence beats eloquence.
Jev Integrations & Adapters#community#github#claude-code
Community
ismaildasci/claude-refereeTypeScript
ismaildasci/claude-refereeTypeScriptAn OpenClaw decision-model provider for any server that speaks the System One API: Kev, a llama.cpp router, or your own. It adds a System One model to the Control UI decision picker, and unlike the official plugin it accepts non-loopback base URLs and an API key.
Jev Integrations & Adapters#community#github#typescript
A context-engineering plugin for DeepSeek Harness that filters tool output, prunes older context and discloses skills progressively, cutting replay payloads by 36.28% in characters, and relies on Jev or Laya as its judge model.
Jev Integrations & Adapters#community#github#typescript
Community
Sev7eEn7/dsh-sieveTypeScript
Sev7eEn7/dsh-sieveTypeScriptA very WIP tool for jev-ification from Harry Solovay: lessons from coding sessions become approved Markdown traits, and a configurable decision model evaluates code one trait at a time while an MCP server handles group-aware approval.
Jev Agents & MCP#community#github#typescript
Community
harrysolovay/traits-pocTypeScript
harrysolovay/traits-pocTypeScriptFrom 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.