AlexlaGuardia/Vigil

**Observability and awareness infrastructure for AI agents.**
Vigil is two layers in one package:
- **MCPWatch** — the silent-failure watchdog for MCP servers. One-line instrumentation for any Python MCP server (FastMCP and low-level mcp.server.lowlevel.Server). Gateways and dashboards already give you latency and error charts. The thing nobody catches is the call that *looks* successful but returns nothing: empty, null, or blank content with no error raised. MCPWatch flags those as a distinct silent status, on top of per-tool latency (p50/p95/p99), error rates, and isError responses. Used in production across 95+ MCP tools.
- **Awareness platform** — daemon-compiled context, signal protocol, session handoff, frame-based tool filtering, MCP server. The nervous system layer most agent frameworks skip.
Most agent memory tools are filing cabinets. Vigil is a stethoscope and a nervous system.
The Problem
**MCP servers fail silently.** A tool returns empty content, the SDK swallows the exception, the agent treats it as "no results found" and you find out three days later from a customer ticket. Latency and error monitoring is now table stakes (gateways, OpenTelemetry, and FastMCP itself emit it). But none of them flag the empty-but-not-errored response — the failure mode your agent quietly hallucinates around. That gap is what MCPWatch exists to close.
**Agents forget everything between sessions.** They load all tools regardless of context (wasting 50K+ tokens). They can't coordinate across sessions or hand off work to each other. Every conversation starts cold.
What Vigil Does
**MCPWatch — the MCP silent-failure watchdog** — One line wraps any Python MCP server (FastMCP or low-level mcp.server.lowlevel.Server). Its headline job: detect silent failures — calls that return empty, null, or blank content with no error raised — and record them as a distinct silent status that shows up in health, per-tool stats, and alerts. It also tracks tool-call latency (p50/p95/p99), per-tool error rates, isError responses, and call volume over time. REST API, CLI, and alert hooks. MIT, no config required.
**Awareness Daemon** — A background process compiles system state every 90 seconds. Agents boot with pre-compiled context in | Emit a signal |
| vigil status | Show current awareness |
| vigil boot | Show compiled hot context |
| vigil frames | List registered frames |
| vigil tools [--frame X] | List tools (optionally filtered) |
| vigil handoff | Write a structured session handoff |
| vigil resume | Resume from last handoff |
| vigil history | Browse compacted signal history |
| vigil agents | List known agents |
| vigil compact | Run signal compaction manually |
| vigil know | Store a knowledge entry |
| vigil recall | Fuzzy-search knowledge |
| vigil knowledge | List all knowledge entries |
| vigil forget | Delete a knowledge entry |
| vigil extract | Auto-extract knowledge from signal patterns |
| vigil export | Export state to markdown |
| vigil mcp-health | MCP server health (calls, errors, latency) |
| vigil mcp-health-check | Probe MCP server in CI (exit 0/1) |