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
- Generic API-catalog MCP server vs one tool per job: a context-bloat experiment — MandeepKaur9407 · 2026-11-16
- Berkeley paper: LLMs answer with stale values even when the update is in context — ombre-ai · 2026-11-16
- skills-gate: one gate skill fronts 148 agent skills at just 389 tokens — Distinct-Pie2389 · 2026-11-16
- Open-weight Karpo-Decision-31B tops Decision Index at 73.9, one forward pass per answer — CodeByPoonam · 2026-11-16
- shadcn boosts @uisdk: one-shot UI rebuild that's instantly E2E-testable by AI — shadcn · 2026-11-16
- AI agent deletes 43,599 lines of OpenClaw test code in one PR — vincent_koc · 2026-11-16