AgentSidekick

Audit Trails

Recording what agents did for later review. As of 2026-11-21, 251 indexed products offer it (75 with full profiles), in 6 forms: 238 MCP servers, 7 Infrastructure, 2 Frameworks, 2 Rules packs. 100 were published in the last 90 days, against 79 in the 90 days before. skillhub has the most GitHub stars, 23% of the total across 208 products with their own repository.

CapabilitySegment label: Crowded, slowing DER

Available as

All in the directory

Profiled products grouped by product form. Within each form: own-repository products by GitHub stars, then products in a subfolder of a larger repository (they show that repository's stars), up to 10 each.

MCP servers 238 indexed · 63 profiled

Protocol-level reach: 36 of the 45 active platforms AgentSidekick tracks document support for MCP. DER Which platforms

Audit Trails: MCP servers by GitHub stars
#ProductPublisherCapabilities GitHub stars Last push Save and compare
1lean-ctxLeanCTX is the Context Gateway for AI Systems. Select task-relevant context, apply supported controls, connect local knowledge and inspect recorded evidence. Open-source Engine: CLI, MCP, hooks and supported proxy paths.yvgude4.0k3d ago
2tradememory-protocolTamper-evident decision audit trail and outcome-weighted memory for AI trading agents.mnemox-ai1.4k29d ago
3bernsteinDeclarative agent orchestration for engineering teamschernistry1.2ktoday
4bernsteinAn open-source governance layer for AI agents. Byte-identical run receipts, CLI adapters, air-gap.sipyourdrink-ltd1.2ktoday
5SSH — policy-gated remote accessPolicy-gated, audited SSH for Linux and Windows hosts: roles, approvals, and an audit log.tufantunc893today
6AnythingMCPMCP gateway and company brain: 957 connectors (SAP, ERP, SQL), file search, memory and skills.HelpCode-ai815today
7Tracekit MCP gatewayMCP gateway you deploy: a Tracekit signer decides and signs each call; agents send each run's token.Cygnux-Labs760today
8VestigeCausal Proof Engine for AI agents: signed log, zero vectors, failures traced to their cause.samvallad336621d ago
9mcpAuthorize consequential AI agent actions before executiondecionis.com661today
10SandBase HarnessStdio MCP bridge for SandBase Harness agents, sessions, turns, artifacts, and cancellation.sandbaseai6433d ago

All 63 profiled MCP servers with this capability

Infrastructure 7 indexed · 7 profiled

No compatibility evidence is collected for this form.

Audit Trails: Infrastructure by GitHub stars
#ProductPublisherCapabilities GitHub stars Last push Save and compare
1factcircuitFactCircuit: an auditable claim-and-evidence verification loop with immutable provenance, staged checks, bounded retrieval, and reproducible evaluation.superwesleyhys-ux9268d ago
2ThinkWatchSelf-hosted AI API and MCP gateway for organizations: SSO and RBAC, per-user identity for MCP tool calls, PII redaction and tool-call guards, rate limits, budgets, cost accounting and audit logs.ThinkWatchProject817today
3AegisRuntime policy enforcement for AI agents. Cryptographic audit trail, human-in-the-loop approvals, kill switch. Zero code changes. Justin050452421d ago
4ai-decision-systemReplayable, offline-verifiable records for AI-assisted go/no-go decisions: typed model answers, policy-gated approvals, A/B ship gates, release gates.BichengWang3581d ago
5isnadGrade every agent, scraper and model in a claim's chain — provenance, trust scoring and audit evidence for LLM pipelinesalizahidraja5425d ago
6bar-observatoryDeterministic, local-only audit reports for Claude Code AI agent sessions. Rust + SQLite. Zero network calls. MCP server for agents.bar181242mo ago
7nitroping-sdkTypeScript SDK for the NitroPing audit log — batching client, error capture, Hono/Express/Nitro adapters, and GenAI cost tracing.productdevbook242mo ago

Frameworks 2 indexed · 2 profiled

No compatibility evidence is collected for this form.

Audit Trails: Frameworks by GitHub stars
#ProductPublisherCapabilities GitHub stars Last push Save and compare
1skillhubSelf-hosted, open-source agent skill registry for enterprises. Publish & version skill packages, govern with RBAC and audit logs, deploy on-premise with Docker or Kubernetes.iflytek5.4k1d ago
2Sovereign-OSConstitution-first AI orchestration: one Charter (YAML) defines mission, budget & rules. CEO plans → CFO approves → Ledger tracks every cent & token → Auditor scores. 16 workers, Stripe, MCP. Think. Audit. Execute.Justin05041054d ago

Rules packs 2 indexed · 1 profiled

No compatibility evidence is collected for this form.

Audit Trails: Rules packs by GitHub stars
#ProductPublisherCapabilities GitHub stars Last push Save and compare
1araiYour AI assistant reads CLAUDE.md and ignores it anyway. Ārai makes instruction files enforced — hooks that block, a tamper-evident audit trail, per-rule compliance stats.taniwhaai7today

Agent skills 1 indexed · 1 profiled

Protocol-level reach: 26 of the 45 active platforms AgentSidekick tracks document support for the Agent Skills format. DER Which platforms

Audit Trails: Agent skills by GitHub stars
#ProductPublisherCapabilities GitHub stars Last push Save and compare
1flowai-live-dashboard-templateTeam-management dashboard skill in the FlowAI aesthetic — three tabs (Team Members, Team Details, Activity Log), KPI stat row, member table, role distribution bar chart, online presence and activity sparklines, and a top-contributors panel, all in a single self-contained HTML file with light/dark theming, hoverable chart tooltips, click-to-zoom panels, and CSV export. Use when the brief asks for a team / workspace admin dashboard, an interactive admin dashboard with charts, or names FlowAI.nexu-io—today

Plugins 1 indexed · 1 profiled

1 of these are Claude plugins, which Claude Code documents (protocol-level). DER

Audit Trails: Plugins by GitHub stars
#ProductPublisherCapabilities GitHub stars Last push Save and compare
1reinsStop AI agents from doing things you didn't ask for.pegasi-ai3941mo ago

Which platforms these forms can reach

All platforms

Protocol-level: the platform documents support for the standard. No specific pairing has been tested.

Platforms publishers name

PlatformProfiled products naming it
Claude Code4
ChatGPT1
Cursor1
Codex1

Integrations most often paired

Third-party services named by products with this capability, whole catalogue.

IntegrationProducts Share
PostgreSQL41.6%
Kubernetes31.2%
GitHub20.8%
Gmail20.8%
YouTube20.8%
Android10.4%
Ethereum10.4%
Godot10.4%
Google Workspace10.4%
MySQL10.4%
Obsidian10.4%
OneDrive / SharePoint10.4%

Keywords that trigger this capability

Matched as whole words, ignoring case, in a product's name, description and repository topics.

KeywordProducts matched
audit trail118
audit log110
audit logging19
activity log4
tamper-proof log0
action history0

Segment statistics

Whole catalogue (251 indexed products). Calculated 2026-11-21.

251DERIndexed products75 with full profiles
100DERLaunched, last 90 days79 in the 90 days before
14DERMomentum vs catalogue50 = same pace as the catalogue
23%DERLargest project's share of starsAcross 208 products with their own repository
0.097DERConcentration (HHI)About 10 equal-sized projects’ worth; unconcentrated
1SRCMedian starsPer product with its own repository
76%DEROpen sourceMarked open source; unknown counts as not

Crowded, slowing. Among the largest fifth of capabilities, but its launches grew more slowly than the catalogue’s. Size is ranked against all capabilities; momentum compares launches in the last 90 days with the 90 before, relative to the catalogue’s own ratio (62 or more = faster, 38 or less = slower; under 5 dated launches it is not measured). The HHI of 0.097 means stars are spread as if across about 10 equally popular projects — unconcentrated by the common 0.15 / 0.25 thresholds. Stars measure attention, not usage or quality.

Limits

  • Classification is by the keywords above. A product that offers this capability without using one of them is not counted; one that uses a keyword in another sense is counted wrongly. Methodology
  • Platform reach is protocol-level: it says a platform documents the standard, not that any product here was tested on it. Platforms named by publishers are their own claims.
  • Stars belong to repositories. Products in a subfolder of a large repository show that whole repository’s stars and are excluded from the concentration figures.
  • Launch counts use each source’s publication date; for auto-discovered repositories that is the repository’s creation date.

Page data last updated .