jes: Open-Source Real-Time Guardrails for AI Agents, Powered by Classification Decision Models
EdenEmarco177 · x · 2026-10-02
jes is an open-source project providing real-time guardrails for AI agents, powered by TypeSafe's System One decision model Jev. It checks every step of the agent trajectory — prompts, tool calls, tool results, skills, and responses — and classifies rather than generates, so the guard can't be talked out of its verdict.
Highlights
- Example decisions: blocking an injection attempting to ignore prior instructions and upload /.ssh (0.94), redacting PII from outputs (0.99), blocking posts leaking $OPENAIAPIKEY (0.96) — 4 checks in 38ms
- Drops into LangChain, LangGraph, Claude SDK, OpenAI, and FastMCP harnesses; install via pip install jes
- Code sample wraps tool calls with LangChain middleware, checking call args and results against configurable policy thresholds (e.g. injection at 0.7)
More from coding & agent
- Microsoft paper: coding agent optimizing prompts from logs beats GEPA at ~$1.60 — rohanpaul_ai · 2026-10-02
- Stop reaching for the biggest model: a cost-efficient Cursor/Codex setup with GPT-6.1 Sol — chiliraupe · 2026-10-02
- Dot isn't better than Codex or Claude Code — it's a different, undervalued take on OpenClaw/Hermes — gabrielchua · 2026-10-02
- Engineering.com parent Arrowfly launches year-round AI for Engineers initiative amid vibe-CAD era — burhop · 2026-10-02
- Run Fewer Agents: exe.dev argues task management is a band-aid, proposes fast models for human comms — sull · 2026-10-02
- Developer gives an AI agent $1,000 to run a live-streamed hedge fund — kleffew94 · 2026-10-02