Edward
Edward — external control plane for AI coding agents: deterministic guardrails + local semantic scorer + resumable interventions.

- GitHub stars
- 5 as of 2026-09-25
- Forks
- 2
- Language
- Python
- License
- MIT
- Created
- 2026-09-22
- Last updated on GitHub
- 2026-09-25
- Added to AionEdge
- 2026-09-25

What Jev does in Edward
The project describes itself this way: Edward — external control plane for AI coding agents: deterministic guardrails + local semantic scorer + resumable interventions. In the Community (unverified) category, Jev typically decides whatever the project describes; the integration has not been confirmed by AionEdge yet.
Verification
Integration not confirmed yet. This repository is public and listed by the community source below, but we have not yet located the code that calls Jev. Check the repository before relying on the integration, and tell us through the submission form if you find it.
Topics
- agent-safety
- ai-agents
- cost-control
- guardrails
- llm
- python
How Community (unverified) projects use Jev
Repositories listed by community Jev lists where we have confirmed the repository exists but have not yet located the code that calls Jev. They stay listed so you can find them; check the repository before relying on the integration.
Also listed in: Security & Guardrails.
Related Jev projects in Community (unverified)
- awesome-jev-robustnessYifan-Lan/awesome-jev-robustnessTests, calibration audits and failure-mode studies of Jev (TypeSafe System One): jaggedness, consistency, injection, abstention.★ 5
rulingbradAGI/rulingTyped, calibrated decisions from a local model. No text generated.★ 6
Python- langchain-skill-routerdeyna256/langchain-skill-routerPer-turn skill selection for LangChain and deepagents agents: a fast judge picks the few skills a turn needs, so a catalog of hundreds stays out of the prompt.★ 4
Python - jit-contextwojciechwiesner/jit-contextArchitectural Moat: JIT-JEV Context OS — Epistemic runtime & JEV System 1 context gate for AI agents (L0 SQLite WAL <3ms, Epistemic Invariants I1–I10, CERN Zenodo DOI: 10.5281/zenodo.22649542).★ 6
Python
dsh-jev-interceptorAskTheWay/dsh-jev-interceptorA DeepSeek Harness plugin that asks Jev to classify the risk of every tool call, auto-approving only with supporting evidence and failing closed.★ 7
TypeScript
jevpdfkylemclaren/jevpdfAsk a PDF in your own words and watch the matching lines light up. React + pdf.js + TypeSafe Jev.★ 3
TypeScript