User repository on GitHub
Jev-powered support ticket router — parallel structured decisions via TypeSafe AI
- Forks
- 0
- Last pushed
- Updated Sep 2026
Repo stats from the GitHub API, cached Oct 2026.
CommunityJev Integrations & Adapters
Jev Router — hj01857655
Zero-dependency Node ticket router that answers routing, priority, urgency, auto-reply, sentiment, and complexity for each ticket in one parallel Jev call.
- Stars
- 1
- Language
- JavaScript
- Published by
- Community
- Author
- hj01857655
- Last verified
- Oct 2026
This is one of several Jev listings for the same project. The canonical entry is Jev Router — gargpratyush.
Highlights
- Six parallel judgments per ticket: two choices, two noul probabilities, and two score values.
- CLI single, batch JSON/JSONL, and HTTP service modes with pretty, json, and jsonl output.
- Fixed team and priority sets prevent out-of-schema routes; concurrency defaults to 10.
- Five-module layout separating Jev client, router mapping, rendering, server, and CLI entry.
Watch out
Zero-dependency Node demo with documented input-token pricing and free output; tune concurrency for large batches. Copy reviewed against the repository README on 2026-10-04, not from running it.
Questions about this entry
Short answers drawn from the linked project or page.
One call asks all six questions together: team choice, priority choice, two noul probabilities, and two score values. Batch mode fans tickets out with tunable concurrency.
Team is limited to billing, security, engineering, product, support, and sales, with priority P0 through P3. Choice cannot return a route outside that fixed set.
Use route for single tickets via flags or stdin, batch for JSON or JSONL files and pipes, and serve for POST /route, POST /batch, and GET /health. Output supports pretty, json, and jsonl.
The client includes retries, timeouts, and error handling, and output formatting plus concurrency controls live in dedicated router, render, server, and CLI modules.
One call per ticket. Ten tickets with six judgments each is sixty structured decisions across ten parallel API calls, which the README puts at about 1.2 seconds. At $0.0578 per million input tokens with output free, ten tickets runs roughly $0.002.
Zero dependencies and Node.js 18 or newer. Clone, export TYPESAFE_API_KEY, then use route for a single ticket via flags or a JSON object on stdin, batch for a JSON or JSONL file, or serve for POST /route, POST /batch, and GET /health. Output is pretty by default and switches to json or jsonl.
Team routing as a choice over billing, security, engineering, product, support and sales; priority as a choice over P0 through P3; urgency and auto-replyable as noul probabilities from 0 to 1; and negativity and handling complexity as scores, where negativity runs 0 friendly to 1 angry and complexity runs 0 simple to 1 complex.
More Jev resources like this
146GitHub stars
A self-hostable API server that fronts text, vision and data endpoints across Ollama, LM Studio, LlamaCpp and a long list of hosted providers, and also runs tool-using agents with sessions. Jev appears separately as a decision provider for typed choice, score and noul questions.
Jev Integrations & Adapters#community#jevbest
Community
donvito/ai-backendsHTML
donvito/ai-backendsHTML21GitHub stars
Self-hosted Rust LLM gateway and load balancer with a System One decision route: one endpoint for OpenAI, Anthropic, local, and Jev-compatible backends, with Model Groups, team budgets, and Postgres usage records.
Jev Integrations & Adapters#community#github
Community
thusinh1969/BrighTO_RouterRust
thusinh1969/BrighTO_RouterRust5GitHub stars
LangChain notebook with runnable Jev examples for ticket triage, model routing, reply guardrails, tool selection and finance inbox checks.
Jev Integrations & Adapters#community#github
5GitHub stars
OpenCode plugin adding an Auto virtual model that asks Jev to pick one of your connected models per turn, failing closed to a fallback when unsure.
Jev Integrations & Adapters#community#github
4GitHub stars
Browser chess lab where LLMs, System One models, and humans play single games, Swiss tournaments, and leagues with Stockfish analysis and cost tracking.
Jev Integrations & Adapters#community#github
Community
dperezcabrera/ai-chess-labPython
dperezcabrera/ai-chess-labPython3GitHub stars
Task plugin that puts TypeSafe's System One endpoint behind a QuantumNous/new-api channel, so clients keep posting `/v1/systemone` while new-api handles auth, routing, model mapping and token billing against either TypeSafe or the Vercel AI Gateway.
Jev Integrations & Adapters#community#jevbest#catalog-import
From the Jev community
Posts from builders shipping with Jev right now.