audit-trail — independent software & tools
-
busabase
⚡ The approval-first, open-source database & knowledge base for AI agents — review & approve every change before it's trusted. Local-first, self-hostable Airtable/Notion alternative.
-
clawock
AI argues. Code settles. The losses stay on the page. A portable investment decision-workflow plugin and verifiable harness, proven on a real HK + US portfolio.
-
Lians
Agent memory for regulated environments. Bitemporal model, tamper-evident audit chain, GDPR crypto-shred.
-
Batoncadence
Vendor-neutral loop manager for AI agents: a self-hosted, governed job board with human approval gates, an immutable audit trail, and Drumline — shared memory every agent reads and writes. MIT, open-core.
-
openSylab
Open-source LIMS for medical diagnostics. ISO 15189-compliant audit trail, RBAC, MFA/TOTP, HL7 v2.5.1 & FHIR R4 native, self-hosted, MIT licensed.
-
agentic-engineering-framework
Governance framework for AI coding agents — enforces task traceability, structural gates, session continuity, and audit trails for Claude Code, Cursor, and Copilot.
-
kyberion
Open-source organization work loop engine — governed multi-agent orchestration with goal-driven workers, evidence-gated missions, and an organizational memory that improves every run.
-
mgit
Sandboxed version control for autonomous coding agents: an agent's untrusted code runs in a per-task microVM, its work stays in an isolated, append-only store, and only the reviewed result lands in your git.
-
polylogue
A local evidence system for AI work—unifying ChatGPT, Claude, Codex, Gemini, and agent histories into one searchable, auditable archive.
-
leashd
Safety-first agentic coding framework. Three-layer safety pipeline (sandbox, YAML policies, human-in-the-loop approval) for AI coding agents. Pluggable runtimes (Claude Code, Codex), autonomous task orchestrator, full audit trail.