# NousResearch/hermes-agent · Cryptographic audit logging for agent actions

## Open now

- 4 issues, 0 PRs open on GitHub.
- #1155: feat: Agent audit log — full history of actions taken
- #5041: Feature: Cryptographic audit trail for tool calls and skill execution via MCP
- #9577: \[Feature\]: Sift governance plugin — Ed25519-signed receipts for agent actions
- #11692: Receipts for self-improving agents: proving which skill version produced which output

These issues and pull requests propose structured, tamper-evident audit logging for agent actions, combining approaches such as hash-chaining, Ed25519 signatures, JSONL/SQLite storage, and CLI tooling to create verifiable records of tool calls and skill executions.

## TL;DR

- 9 member(s): 4 open issue(s), 1 closed issue(s), 0 open PR(s), 0 merged PR(s), 4 PR(s) closed without merging.
- No fix has been merged to main; one or more PRs were attempted (see below).
- **Recommended:** review the prior/competing PR(s) below. A fix was attempted but not merged; your case may extend or revive that work.

## Maintainer resolution verdict

- Internal-tracker verdict over this cluster's issue members: `unresolved`. This is distinct from the fix status above. Weigh it yourself.

## How this cluster was grouped

- Link evidence (`STRUCTURAL_PARTIAL`): some members are connected by structural evidence (shared changed files, or a closing/superseded reference); the rest are joined by an automated relevance judgement over their text.
- Members outside that structural core may belong to a different underlying problem.
- Pairwise link density `0.19`: the share of member pairs that carry a link, counting a structural link in full and a relevance-only link at 0.36. `1.00` means every pair is linked.

## Open related issues

- #1155: feat: Agent audit log — full history of actions taken
- #5041: Feature: Cryptographic audit trail for tool calls and skill execution via MCP
- #9577: \[Feature\]: Sift governance plugin — Ed25519-signed receipts for agent actions
- #11692: Receipts for self-improving agents: proving which skill version produced which output

## Closed / duplicate issues

- #487: Feature: Cryptographic Audit Trail — SHA-256 Hash-Chained Action Log for Tamper-Proof Agent Accountability (inspired by OpenFang)

## Prior & competing PRs

- **#1313: feat: agent audit log — full history of actions taken**. closed without merge
  - maintainer direction: category `uncategorized`; implication `needs_llm`
- **#1819: feat(audit): structured JSONL + SQLite audit log (closes #1155)**. closed without merge
  - maintainer direction: category `implemented_elsewhere`; implication `superseded`
- **#1944: feat: structured audit log system — full agent action trail with CLI, problem detection, and self-query**. closed without merge
  - maintainer direction: category `uncategorized`; implication `needs_llm`; refs `#1819`, `#1819`
- **#13082: feat(plugins): add signet — cryptographic audit trail plugin (fixes #487)**. closed without merge
  - maintainer direction: category `uncategorized`; implication `needs_llm`

## Fix status

- No merged fix on record.
- Subsystem: `agent`