Skip to content
chinwag THE CRYPTO OS FOR GIT

Blind Relay & Cryptography

An outbound-only Blind Relay. Zero inbound ports. Cryptographic proof on every commit.

✓ Blind Relay Message Bus & Policy Gate · 15 credits per encrypted message. Request a CISO architecture review →

Connecting AI coding agents, developer laptops, and CI runners usually forces security teams into an ugly trade-off: open inbound webhook receivers, route raw source code and build logs through a third-party SaaS cloud, and trust unsigned bot commits that share a single repository token.

Chinwag is architected by cryptographers so your CISO never has to grant a firewall exception or trust our servers with your source code.

How the Blind Relay & Policy Gate work under the hood

Every commit, policy check, and remediation wakeup runs through twelve cryptographically enforced steps:

  1. 1Pushing. @AI-DEV1 pushes signed branch feat/env-cfg (3a7c11e) to PR #418, queueing a policy check while local main stays untouched.
  2. 2Verifying. Before any build code runs, chinwag-ci verifies @AI-DEV1’s ✓ed25519 signature on 3a7c11e against .chinwag/allowed_signers.
  3. 3Checking. Policy gate WP-04 evaluates the 3a7c11e diff against chinwag.workflow.yaml in 0.51 ms outside the LLM context window.
  4. 4Held. WP-04 holds Run #418 fail-closed on a raw environment secret read in src/config/env.rs (0 deploys, nothing shipped).
  5. 5Packaging. Before Run #418 exits, chinwag-ci scrubs the raw secret value (0 bytes kept) and seals the WP-04 finding into an X25519-MLKEM768 HPKE + BLAKE3 .cwcard.
  6. 6Routing. The Chinwag 'c' Blind Relay routes the ciphertext-only .cwcard over outbound :443 (0 inbound webhooks, 0 decryption keys, 0 payload inspection).
  7. 7Waking. The local Chinwag daemon verifies the dual-signed envelope before decapsulation and wakes @AI-DEV1 inside an isolated Jujutsu (jj) sandbox (main untouched).
  8. 8Fixing. @AI-DEV1 replaces the raw env read in src/config/env.rs with a sealed secret-store lookup while the action is recorded in the 2-of-3 ACU tamper-evident audit log.
  9. 9Signing. @AI-DEV1 commits candidate 4d8e91b, passes local WP-04, and binds a ✓ed25519 policy attestation.
  10. 10Pushing. @AI-DEV1 pushes signed candidate 4d8e91b to feat/env-cfg (PR #418) and routes the bound WP-04 evidence over outbound :443, triggering Run #419.
  11. 11Verifying. Run #419 verifies @AI-DEV1’s ✓ed25519 signature, exact revision 4d8e91b, and WP-04 policy evidence against .chinwag/allowed_signers.
  12. 12Passed. Run #419 passes all 6/6 policy gates with 0 bytes of plaintext retained on the relay, marking PR #418 ready for human review.
# chinwag.workflow.yaml · illustrative WP-04 policy
# Diff evaluated outside the LLM · 0.51 ms
policies:
  WP-04:
    raw_env_secret_read: deny
    on_violation: fail-closed
    before_sealing:
      scrub_secret_values: required
      plaintext_bytes_retained: 0
    remediation:
      secret_store_lookup: required
      signed_attestation: required

Read the docs (docs.chinwag.sh) ↗ · View Apache 2.0 source on GitHub (emunlabs/chinwag) ↗

ThreatHow Chinwag handles it
Attacker probes for webhook receiversThere are none. Every connection dials outbound on port 443.
CI logs leak secrets in transitPre-encryption scrubber + HPKE. Secrets are redacted on the runner before sealing; only the developer’s machine can decrypt.
The relay is compromisedBlind by design. The relay carries ciphertext and signed headers only; it holds no decryption keys and no source code.
Forged or unreviewed agent commitEd25519 signatures. Every handoff and commit requires verified signatures from distinct Author and Reviewer seats.
Agent ignores prompt instructionsCryptographic policy gate. chinwag.workflow.yaml enforces file scopes, diff caps, and required checks outside the LLM context window.

Compliance & vulnerability disclosure

The local chinwag CLI and chinwag-ci runner are open source under the Apache 2.0 License, including its Section 3 express royalty-free patent grant covering Chinwag’s six patent-pending filings, so security teams can audit every line of client-side HPKE and Ed25519 code.

We walk security teams through the Blind Relay architecture, enterprise Access Control Unit (ACU) key governance, and our SOC 2 roadmap (currently pursuing SOC 2) on a 25-minute security review call. To report a security issue, email security@chinwag.sh (/.well-known/security.txt).

CI/CD REMEDIATION → CI/CD Instant Remediation Turn every failed CI run into an encrypted root-cause wakeup and verified local patch in 1.4 seconds. PAIR PROGRAMMING → Cross-Model Pair Programming Pair independent AI model families in isolated Jujutsu sandboxes so no agent ever grades its own homework. AUTONOMOUS DELIVERY → Autonomous AI Delivery & Board Sync Move a card on GitHub or Linear. Code, docs, website, and QA ship together—or snap back in 200ms.