Skip to content
View selfradiance's full-sized avatar

Block or report selfradiance

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.

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
selfradiance/README.md

selfradiance

I build narrow proofs for governing AI agents before, during, and after they act. This profile is a map of governed agent harness primitives: small local repos that test one seam at a time. It is not a completed framework, not a platform, and not a claim that agents are safe.

AgentGate remains central as the after-action accountability substrate: identity, bonds, action records, settlement, slash/release. The wider ecosystem now also touches before-ingestion, before-context, before-action, during-execution, after-mutation, and adversarial-testing seams.

Start here

If you're new, use this order:

  1. agentgate-governed-writefile-demo - the fastest outsider-readable proof path through governed write_file.
  2. agentgate-mcp-firewall - the narrow execution layer that checks whether governed filesystem calls produced the effects they claimed.
  3. agentgate - the deeper after-action accountability substrate underneath that path.

Governed agent lifecycle map

These are narrow local proofs and partial proofs, not a finished harness. The fuller topology is in HARNESS_MAP.md.

AgentGate arc

For the strongest current proof path, start with agentgate-governed-writefile-demo. Then read agentgate-mcp-firewall for the current filesystem-effect verification layer. Read agentgate after that if you want the accountability engine underneath both; it is the substrate, not the first repo most cold visitors should begin with.

Pinned Loading

  1. agentgate-governed-writefile-demo agentgate-governed-writefile-demo Public

    Smallest outsider-readable proof path through AgentGate + MCP Firewall: governed write_file, independent on-disk verification, and inspectable audit artifacts.

    TypeScript 2 1

  2. agentgate-mcp-firewall agentgate-mcp-firewall Public

    Governance proxy for MCP tool calls with narrow independent verification for governed write_file and delete_file effects.

    TypeScript 1

  3. agentgate agentgate Public

    Collateralized execution engine for AI agents: bond-and-slash accountability with Ed25519 identities, bounded exposure, and progressive trust tiers.

    TypeScript 5

  4. reapproval-gate reapproval-gate Public

    Local deterministic CLI that checks proposed agent actions against approved scope and flags when human reapproval is required.

    TypeScript

  5. rollback-receipt rollback-receipt Public

    Local deterministic CLI that snapshots explicitly listed files before AI-agent mutations and produces inspectable rollback receipts.

    TypeScript

  6. work-session-ledger work-session-ledger Public

    Local deterministic CLI that assembles inspectable receipts for AI coding-agent work sessions from declared artifacts.

    TypeScript