Proposal: Agent OS — Governance Kernel for AI Agents (Sandbox)#102
Closed
imran-siddique wants to merge 2 commits into
Closed
Proposal: Agent OS — Governance Kernel for AI Agents (Sandbox)#102imran-siddique wants to merge 2 commits into
imran-siddique wants to merge 2 commits into
Conversation
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Author
|
Migration update: This project has officially moved to microsoft/agent-governance-toolkit under the Microsoft org. The code in this PR has been updated to reference the new location. Install via: All old personal repos ( |
Author
|
Closing — this project has moved to microsoft/agent-governance-toolkit. Will re-submit fresh proposals from the Microsoft repo. Thank you! |
imran-siddique
added a commit
to microsoft/agent-governance-toolkit
that referenced
this pull request
Apr 20, 2026
- AAIF: Updated from closed aaif/technical-committee#1 to The-AI-Alliance/community#58 - LF AI: Updated from closed lfai/proposing-projects#102 to new #104 Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
imran-siddique
added a commit
to imran-siddique/agent-governance-toolkit
that referenced
this pull request
Apr 20, 2026
- AAIF: Updated from closed aaif/technical-committee#1 to The-AI-Alliance/community#58 - LF AI: Updated from closed lfai/proposing-projects#102 to new microsoft#104 Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
imran-siddique
added a commit
to microsoft/agent-governance-toolkit
that referenced
this pull request
Apr 20, 2026
* docs: update AAIF and LF AI proposal links to active submissions - AAIF: Updated from closed aaif/technical-committee#1 to The-AI-Alliance/community#58 - LF AI: Updated from closed lfai/proposing-projects#102 to new #104 Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * feat(e2e): Double Ratchet for per-message forward secrecy (#1223) Implements the Signal Double Ratchet algorithm on top of X3DH shared secrets for E2E encrypted agent messaging with forward secrecy and post-compromise security. New files: - agentmesh/encryption/ratchet.py — Double Ratchet implementation - DoubleRatchet (init_sender/init_receiver, encrypt/decrypt) - DH ratchet step on conversation turn change (X25519) - Symmetric chain ratchet (HMAC-SHA256) - ChaCha20-Poly1305 message encryption - Skipped message key caching (configurable max) - Serializable RatchetState (to_dict/from_dict) - MessageHeader and EncryptedMessage with serialization - tests/test_ratchet.py — 18 tests covering: - Single message, multi-message, bidirectional conversation - Forward secrecy (different keys per message) - DH ratchet advances on turn change - Out-of-order message delivery - Max skip enforcement - Tampered ciphertext rejection - Associated data authentication - State serialization roundtrip + session resumption Uses only existing deps: PyNaCl + cryptography. Closes #1223 Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> --------- Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Author
|
Correction (May 2026): For the record, this early proposal listed "4 external contributors" as a key metric. Those individuals were community contributors, not maintainers. The project's current maintainers are Imran Siddique, Jack Batzner, and Elton Carr, all Microsoft. The active proposal is now at PR #104 with corrected information. This project also uses AI-assisted development tools (GitHub Copilot, Claude); all AI-generated code is human-reviewed before merge. |
imran-siddique
added a commit
to imran-siddique/agent-governance-toolkit
that referenced
this pull request
May 4, 2026
…rosoft#1229) - AAIF: Updated from closed aaif/technical-committee#1 to The-AI-Alliance/community#58 - LF AI: Updated from closed lfai/proposing-projects#102 to new microsoft#104 Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
imran-siddique
added a commit
to imran-siddique/agent-governance-toolkit
that referenced
this pull request
May 4, 2026
…1230) * docs: update AAIF and LF AI proposal links to active submissions - AAIF: Updated from closed aaif/technical-committee#1 to The-AI-Alliance/community#58 - LF AI: Updated from closed lfai/proposing-projects#102 to new microsoft#104 Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * feat(e2e): Double Ratchet for per-message forward secrecy (microsoft#1223) Implements the Signal Double Ratchet algorithm on top of X3DH shared secrets for E2E encrypted agent messaging with forward secrecy and post-compromise security. New files: - agentmesh/encryption/ratchet.py — Double Ratchet implementation - DoubleRatchet (init_sender/init_receiver, encrypt/decrypt) - DH ratchet step on conversation turn change (X25519) - Symmetric chain ratchet (HMAC-SHA256) - ChaCha20-Poly1305 message encryption - Skipped message key caching (configurable max) - Serializable RatchetState (to_dict/from_dict) - MessageHeader and EncryptedMessage with serialization - tests/test_ratchet.py — 18 tests covering: - Single message, multi-message, bidirectional conversation - Forward secrecy (different keys per message) - DH ratchet advances on turn change - Out-of-order message delivery - Max skip enforcement - Tampered ciphertext rejection - Associated data authentication - State serialization roundtrip + session resumption Uses only existing deps: PyNaCl + cryptography. Closes microsoft#1223 Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> --------- Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Project Proposal: Agent OS — Governance Kernel for Autonomous AI Agents
Requested Level: Sandbox
Summary
Agent OS is an open-source governance kernel for autonomous AI agents providing runtime policy enforcement, capability sandboxing, inter-agent trust verification, and kill-switch controls.
The ecosystem consists of 5 interoperating packages:
Key Metrics
Alignment with LF AI Mission
As AI agents become increasingly autonomous, governance infrastructure is critical for safe deployment. Agent OS provides this as a neutral, open-source project — preventing vendor lock-in and enabling a shared governance standard.
Links