タグ：python

python タグの付いた Jev GitHub プロジェクトを検索・並べ替えし、元のリポジトリを確認できます。

599jev-browser-local
Run jev-browser on a fully local JEV-style decision engine (no cloud API). Warm-browser fork, VRAM guard, measured benchmarks, run traces.
rorshopping/jev-browser-local · Python
31
python
600jev-builder-loop
Grok skill: Jev as a judgment sensor in a builder-agent loop (priors × probabilities → next act)
rainbowpuffpuff/jev-builder-loop · Python
30
python
603jev-demofast
One sentence in, a product demo video out. Jev drives your real product in a browser; an index built from your source code guides it.
q3learners/jev-demofast · Python
30
browser-automationcloudflare-workers-aidemo-videonextjsproduct-demopython
604jev-exploration
Jev (TypeSafe) exploratory thread: claim audit, live demos, and runnable code
SamuelSacco/jev-exploration · Python
30
python
609jev-guardrails
Comparing LLM-as-judge vs TypeSafe Jev for agent guardrails: same rules, same agent, measured on cost, latency, calibration and coverage.
deepansh-saxena/jev-guardrails · Python
31
python
610jev-mcp
Local MCP server exposing TypeSafe Jev (System One decision model) as native Claude Code / Codex tools
Songokou1983/jev-mcp · Python
30
python
613jev-mcp-server
MCP server for Jev (TypeSafe System One): the three official question types — choice, score, noul — plus batch classify. Calibrated probabilities, ~0.5s, <$0.001/call.
wangkuangkuang/jev-mcp-server · Python
30
classifierllmmcpmodel-context-protocolpython
616jev-nethack
TypeSafe's Jev model plays NetHack 5.0: code lists the legal moves, Jev picks one, no LLM in the loop
statico/jev-nethack · Python
31
ai-agentsgame-aihardfoughtnethackpythonroguelike
617jev-oncall
Incident triage on TypeSafe Jev — the model judges, plain code decides. Routing on probability distributions with a human-review middle band and fail-open defaults.
mingleiw/jev-oncall · HTML
30
python
618jev-physical-ai
Putting TypeSafe's Jev to work on robots, fleets, and edge hardware — real measured numbers, honestly caveated.
robokrunch/jev-physical-ai · Python
30
benchmarkedge-aiphysical-airoboticspython
619jev-relevance
Drop-in relevance filter for LangChain RAG retrievers powered by TypeSafe Jev.
saksham-malhotra-27/jev-relevance · Python
30
python
622jev-rl
JEV Reinforcement Learning: four classic games trained with JEV-powered rewards, reproducible experiments and checkpoint replays.
Bring-AI/jev-rl · Python
30
python
623jev-route
jev-route: TypeSafe Jev ecosystem repository.
mcftira/jev-route · Python
31
python
627jev-second-brain
Local-first Markdown memory alignment and source-linked search with optional Jev judgments
fellowship-dev/jev-second-brain · Python
31
knowledge-managementlocal-firstmarkdownobsidianrerankingsecond-brainpython
629jev-skill-router
Keep skill catalogs outside the main LLM context. Jev selects relevant skills through one read-only MCP tool.
himomohi/jev-skill-router · Python
31
agent-skillsclaude-codecodexcontext-engineeringllmmcppython
634jev-storyboard-lab
Google ADK vs Microsoft Agent Framework for structured-output agents, with TypeSafe Jev as a vendor-neutral QC gate
jimmyliao/jev-storyboard-lab · Python
30
python
639Jev4Mellea
Jev adapter to Mellea
SoundBlaster/Jev4Mellea · Python
30
python
649llm-schema-lite
“LLM-ify” your JSON schemas
rohitgarud/llm-schema-lite · Python
30
python
671tiershift
Shift every LLM call to the cheapest model that can handle it. Routing decided by TypeSafe Jev in ~180 ms. No training data. Policy in plain YAML. TypeScript and Python.
iamvatsalpatel/tiershift · TypeScript
31
ai-agentscost-optimizationllmmodel-routingopenai-compatibleproxypython
674truetype.ai-open
Open source replica of Truetype AI using open weight models
stephenlb/truetype.ai-open · Python
30
python
677typesafe-assist
Home Assistant Assist conversation agent powered by TypeSafe's Jev (System One) model
JanOstrowka/typesafe-assist · Python
31
python

539 件中 151–200 件