Skip to content
View chernistry's full-sized avatar
:electron:
Something great is coming
:electron:
Something great is coming

Block or report chernistry

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
chernistry/README.md

Alex Chernysh

Applied AI Systems Engineer · multi-agent, RAG, MCP · evals.

Maintaining Bernstein: open-source governance layer for AI agents (Apache-2.0). Declarative rules, deterministic scheduling, run records you can verify and replay.

Upstream work

  • TRACE Trust Record spec: the reproducibility claim for deterministic re-execution (§3.1.4), its schema and conformance vectors, schema/docs coverage guards, the software-only producer annex.
  • CoSAI WS4 (OASIS Open Project): reviews on the agent-containment paper.
  • Hosted TRACE verifier: mcp.bernstein.run.

🇮🇱 Tel Aviv · LinkedIn · hello@alexchernysh.com · alexchernysh.com

Pinned Loading

  1. sipyourdrink-ltd/bernstein sipyourdrink-ltd/bernstein Public

    The open‑source AI Agents Governance & Orchestration framework: write the rules declaratively, Bernstein enforces them and produces the verifiable, replayable record. Free, Apache-2.0. https://bern…

    Python 1.2k 170

  2. sipyourdrink-ltd/bernstein-mcp sipyourdrink-ltd/bernstein-mcp Public

    Stateless MCP endpoint that verifies bernstein run receipts and hash chains — https://mcp.bernstein.run/

    TypeScript

  3. sipyourdrink-ltd/bernstein-landing sipyourdrink-ltd/bernstein-landing Public

    Website for Bernstein, the open-source governance layer for AI agents. Next.js, plus the machine-readable surfaces that let agents read the project without scraping HTML.

    TypeScript

  4. trace-spec trace-spec Public

    Forked from agentrust-io/trace-spec

    TRACE: Trust Runtime Attestation and Compliance Evidence. Open attestation standard for agentic AI governance.

    Python