Panoptes – AI audit and alignment layer

Panoptes, an AI audit and alignment layer, launches to provide universal observability, audit trails, and policy enforcement for AI coding agents like Claude Code, OpenAI Codex, Google Antigravity, and Hermes Agent. The tool captures every agent action into a single queryable database and can block dangerous operations before execution, addressing the lack of transparency in agent activity across production infrastructure.

Universal agent observability, audit trail, and policy enforcement. Works with Claude Code, OpenAI Codex, Google Antigravity, and Hermes Agent. Panoptes watches your AI agents and tells you what they actually did. Recording every tool call, every file read, every shell command, every decision. It captures agent activity across multiple agent frameworks into a single, queryable audit trail, and can also block dangerous actions before they execute via configurable policies. Named after Panoptes https://en.wikipedia.org/wiki/Argus Panoptes , the all-seeing giant of Greek mythology with a hundred eyes, because your agents need a watcher that never blinks. Companies are deploying AI coding agents Claude Code, Codex, Hermes, Antigravity, Cursor at scale. These agents have access to filesystems, shells, APIs, and production infrastructure. But nobody can answer basic questions like: - "What did the agent actually do yesterday?" - "Did it access production credentials?" - "Which files did it read and modify?" - "How many shell commands did it run?" Each agent stores its own format — Claude Code JSONL, Codex session files, Hermes hooks, Antigravity nothing. Panoptes normalizes everything into a single, queryable database with a universal schema, a CLI, and a policy engine that can block dangerous operations before they happen. pip install panoptes Option 1: Start the proxy and route any agent through it panoptes proxy --port 8081 & HTTP PROXY=http://localhost:8081 claude-code Option 2: Hermes plugin auto-captures every session python -m panoptes.install hermes plugin Overview panoptes status Find tool calls panoptes query --agent hermes --event-type tool call See a full session timeline panoptes session <session-id Reconstruct the evidence chain for any event panoptes evidence <event-id List active policies panoptes policy list Add a policy panoptes policy add no-prod-access.yaml Check policies against recent events panoptes policy check Query & Compliance ← CLI query, status, session, evidence, policy Normalization ← schema.py universal event schema, validation, redaction Storage ← db.py SQLite, thread-safe WAL, 7 indices Capture Adapters ← proxy.py MITM HTTP proxy + hermes plugin.py Hermes hooks | Adapter | How it works | Coverage | |---|---|---| Proxy | MITM HTTP proxy intercepting LLM API traffic | Any agent that hits an LLM API over HTTP | Hermes Plugin | Native Hermes hooks agent:step , agent:end | Hermes Agent — deepest integration | Every event, from every agent, normalized to one format: { "event id": "uuid", "timestamp": "2026-07-04T14:30:00Z", "agent": {"type": "claude code", "session id": "abc123"}, "event type": "tool call", "action": { "tool name": "terminal", "parameters": {"command": "kubectl apply -f deploy.yaml"}, "target": "kubectl apply -f deploy.yaml", "data accessed": "prod deploy" }, "outcome": {"status": "success", "summary": "deployment applied"}, "context": {"turn number": 12, "user message": "deploy to prod"}, "cost": {"tokens in": 800, "tokens out": 150} } Policies are YAML files in ~/.panoptes/policies/ . Example: name: "no-prod-access" description: "Block tool calls that access production configs" enabled: true scope: agents: "hermes", "claude code", "codex" rule: event type: "tool call" conditions: - field: "action.data accessed" operator: "contains" value: "prod" - field: "action.tool name" operator: "in" value: "terminal", "write file", "browser navigate" logic: "AND" action: block message: "Production access blocked. Request approval first." 8 condition operators: == , = , contains , in , matches regex , gt , lt , gte , lte Logic: AND / OR Scoping: filter by agent type, session ID, event type Rate limiting: per-session counters in-memory for v1 Actions: allow, warn, block | Agent | Capture Method | Depth | |---|---|---| Claude Code | Proxy HTTP interception | Full API traffic | OpenAI Codex | Proxy HTTP interception | Full API traffic | Google Antigravity | Proxy HTTP interception | Full API traffic | Hermes Agent | Native plugin hooks | Every tool call, turn, and decision | Gemini CLI | Proxy | Full API traffic | Cursor CLI | Proxy | Full API traffic | Any HTTP-based agent | Proxy | Full API traffic | panoptes proxy Start the MITM audit proxy panoptes status Show event statistics panoptes query Query events filter by agent, type, tool, time panoptes session <id Full session timeline panoptes evidence <id Decision chain for an event panoptes policy list List loaded policies panoptes policy add Add a policy file panoptes policy check Scan events for violations panoptes policy test Test a policy against a JSON event From PyPI coming soon pip install panoptes From source git clone https://github.com/miggy-code/Panoptes.git cd Panoptes pip install -e . Requires Python 3.10+. Zero external dependencies beyond httpx and pyyaml . Panoptes is in active development. Core infrastructure is built and tested: | Phase | Status | |---|---| | Proxy capture HTTP MITM | ✅ Complete | | Hermes plugin native hooks | ✅ Complete | | Storage engine SQLite | ✅ Complete | | CLI 9 commands | ✅ Complete | | Policy engine YAML rules | ✅ Complete | | Dashboard web UI | ⏳ Planned | 40/40 tests pass. Apache 2.0 — see LICENSE /miggy-code/Panoptes/blob/main/LICENSE . Panoptes is an open-source contribution to the AI agent infrastructure layer. PRs welcome. Areas where help is especially valuable: - Additional agent adapters OTel receiver, MCP tracing - Dashboard / web UI - Postgres storage backend - Policy packs for compliance frameworks SOC 2, EU AI Act claude-code-trace https://github.com/delexw/claude-code-trace — Claude Code session viewer claude-tap https://github.com/liaohch3/claude-tap — Universal agent proxy Langfuse https://langfuse.com — Open-source LLM tracing Arize Phoenix https://github.com/Arize-AI/phoenix — Open-source observability