Spike: Jev as a judgement layer to cut model cost
Issue: a multi-agent orchestration platform plans to move judgment out of its model-of-thought and onto Jev, framed as cutting cost while holding quality.
- GitHub stars
- 6 as of 2026-09-22
- Forks
- 5
- Language
- Python
- License
- MIT
- Created
- 2026-06-16
- Last updated on GitHub
- 2026-09-24

What Jev does in Spike: Jev as a judgement layer to cut model cost
The project describes itself this way: Issue: a multi-agent orchestration platform plans to move judgment out of its model-of-thought and onto Jev, framed as cutting cost while holding quality. In the Community additions category, Jev typically decides a single well-defined judgment, such as a label, a score or a yes/no check.
Verification
Verified. We confirmed this repository and its Jev relevance through the GitHub API and the source lists below. A specific file link has not been recorded yet.
How Community additions projects use Jev
Projects added from community lists and direct submissions. Many are small, single-purpose experiments, which makes them some of the easiest places to see how a Jev question is framed in real code.
Related Jev projects in Community additions
- BrowserClawGoldenLoaf24h/browserclawBrowser automation: Zero-lock, session-preserving Chrome MCP server that couples a local Jev System One semantic micro-loop (`chrome_act_toward_goal`) with an 85%+ pruned DOM tree (Shadow DOM & iframe pierced), dispatching native CDP events (`isTrusted: true`) on active logged-in sessions without focus theft.★ 6
TypeScript - rotomRyanKung/rotomLocal gateways: OpenAI- and Anthropic-compatible API gateway that carries Jev through its model catalog and evaluation path.★ 5
Rust - jev-goStumble/jev-goGo ecosystem: community Go SDK for Jev.★ 5
Go
Okobartlomein/okoDeveloper tooling: local code search for coding agents that shortlists function-level chunks with ripgrep and BM25, asks Jev a `Noul` relevance question per chunk across three parallel requests, and returns the accepted ones as excerpts through MCP; the cutoff and excerpt selection live in code.★ 5
Rust- Visual-JEVjiangxiluning/Visual-JevA visual Jev—a native multimodal Jev based on Qwen3.5-4B—that supports direct image input without requiring modality conversion.★ 7
Python
jev-usecaseskenhuangus/jev-usecasesReference harnesses: a set of production-shaped use-case harnesses built around confidence-gated decision logic.★ 5
Python