User repository on GitHub
Give your AI agent a CLI companion who has access to TypeSafe AI's Jev.
- Forks
- 0
- Last pushed
- Updated Sep 2026
Repo stats from the GitHub API, cached Oct 2026.
Jev directory
CommunityJev Tools & CLIs
Typesafeai CLI
An agent-first CLI for System One: ask, rank, extract, verify, screen, find, and decide from the shell, with an installable agent skill. Published on PyPI.
- Stars
- 2
- Language
- Python
- License
- MIT
- Reading time
- 3 min
- Published by
- Community
- Last verified
- Sep 2026
About this project
CLI for TypeSafe Jev. Run it from a shell, or let an agent run it. Jev answers noul, choice, and score questions over JSON state. It does not chat, and it only sees what you send. Invalid answers fail closed. Unused speculative heads cannot act. Ranked find lines are not evidence when the document has no answer. Python 3.10+. API key: TypeSafe console. pip install typesafeai-cli is the same package. typesafe ask takes a state file and a questions file. Point each instruction at state with backticks.
Quoted from the project's README. Read the full README.
Highlights
- Installs via pipx or pip as typesafeai-cli; requires Python 3.10+ and TYPESAFE_API_KEY.
- Exit codes: 0 answered, 1 request failed or invalid answer, 2 bad flags or questions.
- `typesafe decide` maps answers to yes/no/uncertain without making any HTTP call.
- `skills install` mirrors `npx skills add` and writes a pointer into ~/.claude/CLAUDE.md, ~/.codex/AGENTS.md, or ~/.grok/rules/typesafe-cli.md.
- Question instructions reference state fields with backticks, e.g. "Does `message` request a refund?"
Quickstart
bash
export TYPESAFE_API_KEY=apikey_...
pipx install typesafeai-cli
typesafe ask --state-file state.json --questions-file questions.json
typesafe noul "Does this request a refund?" --state "I was charged twice."Watch out
It is a thin, non-chatting client: it needs a TypeSafe API key, only sees the state you send, and fails closed on invalid answers.
Questions about this entry
Short answers drawn from the linked project or page.
It does not chat and only sees the state you send. Invalid answers fail closed, unused speculative heads cannot act, and ranked find lines are explicitly not evidence when the document has no answer. Exit codes separate the cases: 0 answered, 1 request failed or invalid answer, 2 bad flags or questions.
No. This one is Python 3.10 or later and installs with pipx or pip as typesafeai-cli, with a curl install script on the releases page as a third option. It needs TYPESAFE_API_KEY from the TypeSafe console, and auth status reports whether a key is loaded and nothing more.
No HTTP call. It maps answers already on disk to yes, no or uncertain, which makes it safe to put in a policy path that must not spend or wait. The mapping is local to the package, so the thresholds it applies are yours to inspect rather than something the model negotiated.
Keep those JSON files under ${TMPDIR:-/tmp}/codex/<project>/. Instructions reference state fields with backticks, for example Does `message` request a refund?, and skills install mirrors npx skills add, writing a pointer into ~/.claude/CLAUDE.md, ~/.codex/AGENTS.md or ~/.grok/rules/typesafe-cli.md when run globally.
choice and score for a single question of that shape, find to search a file, rank to order a JSON shortlist, extract to pick a span already present in the text, verify to check a claim against a source, screen for jailbreak, injection, sensitive data and harm, suggest-skill which returns at most one skill name, models for the model aliases, smoke to run the live docs quickstart, and agent schema for a JSON command tree.
Three: examples/ticket, examples/code-change and examples/fan-out, each a full copy of a state file and a questions file. They follow the same two-file shape as typesafe ask, so you can point the CLI at one to see a working question set before writing your own, and they cover a support ticket, a code change and a fan-out case.
It asks. typesafe agent schema prints the JSON command tree, so an agent reads the command set and its flags straight from the CLI rather than guessing or shelling out blind. suggest-skill is the constrained sibling: it returns at most one skill name and nothing more, and skills install is the supported way to wire the CLI into an agent's project or global configuration.
More Jev resources like this
grep, sort, cut and uniq that match by meaning: each line whose Jev Noul clears the threshold survives grev, sibling filters route by Choice and rank by Score, and the output is always your own input, never generated text.
Jev Tools & CLIs#community#cli#coreutils
Community
aurorainfra/grevGo
aurorainfra/grevGoA cross-platform memory layer for AI coding agents: conversations from Claude Code, Codex, DeepSeek Harness, OpenClaw, and OpenCode become Markdown memories indexed in Milvus, with optional Jev reranking through the TypeSafe API.
Jev Tools & CLIs#community#python#agents
Community
zilliztech/memsearchPython
zilliztech/memsearchPythonA local deep-research tool that turns your own PDF, DOCX, PPTX, image, TXT, or Markdown files into a structured report, using TypeSafe's Jev to rerank Qdrant chunks and verify evidence coverage while an LLM plans and writes.
Jev Tools & CLIs#community#github#python
Community
oqura-ai/deepdocPython
oqura-ai/deepdocPythonAn MCP server exposing ten Jev judgment tools, including verify, screen, find, rerank, classify, review, and gate, each returning typed probabilities in roughly 150 to 500 ms.
Jev Tools & CLIs#community#typescript#mcp
Community
jkudish/jev-mcpJavaScript
jkudish/jev-mcpJavaScriptA single-binary Go MCP server exposing one evaluate tool for noul, choice, and score questions, with one-command registration for Claude Code, Claude Desktop, and Codex.
Jev Tools & CLIs#community#go#mcp
Community
itsmostafa/typesafe-mcpGo
itsmostafa/typesafe-mcpGoA Rust CLI that ranks agent skills for the next step with a two-stage Jev pass plus lexical prefiltering, with Claude Code hooks, a TUI, abstention, and --why-not explanations.
Jev Tools & CLIs#community#rust#cli
Community
Dicklesworthstone/skillrankerRust
Dicklesworthstone/skillrankerRustFrom 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.