numbat
Visibility into AI agent activity on endpoints, with on-device detection, optional pre-action blocking, and forensic reconstruction.
perplexityai/numbat
View on GitHub ↗Visibility into AI agent activity on endpoints, with on-device detection, optional pre-action blocking, and forensic reconstruction.
numbat grew +2.9% in the last 30 days, ranks 81st of 340 in Observability & Tracing, actively maintained, last commit 2 days ago.
Star trajectory
82 days tracked+2.9% in 30d, above the Observability & Tracing median of +1.1%.
Last commit 2 days ago, fresher than the median of 5d.
How it compares in Observability & Tracing
Ranked 81st of 340 by stars.
Related repos
Ranked by shared tags, then keywords, then starsWhere numbat sits
Hover or focus a node for details. Click to open it.
- This repo
- Related repo
- Tag or category
Tracekit records what your AI agents do, decides each tool call before it runs, and gives you a signed record…
+649 (+433%) in 30d · Committed today · Python · MIT
Shares Evaluation & Guardrails, Observability & Tracing
Open-source runtime AI agent security tool - monitors and controls AI agents, catching malicious tool use…
+10 (+1.7%) in 30d · Committed 31d ago · Python · Apache-2.0
Shares Evaluation & Guardrails, Observability & Tracing
AI Agent Identity and Access Management and Inference Firewall
+148 (+54%) in 30d · Committed 28d ago · Python
Shares Evaluation & Guardrails, Observability & Tracing
Execution-Layer Security (ELS) for AI agents — policy-enforced shell with audit.
+12 (+3.0%) in 30d · Committed 14d ago · Go · Apache-2.0
Shares Observability & Tracing, Evaluation & Guardrails
The black box for AI-written code. Passive decision graph linking every commit to the agent prompts behind it…
-39 (-12%) in 30d · Committed 11d ago · Rust · Apache-2.0
Shares Observability & Tracing, Evaluation & Guardrails
Wireshark-like forensic analysis for Model Context Protocol communications Capture, inspect, and investigate…
+0 (+0.0%) in 30d · Committed 209d ago · JavaScript · Other license
Shares Evaluation & Guardrails, Observability & Tracing
Governance, risk, compliance and security for agentic AI, non-human identities and swarms. A Rosetta Stone…
+9 (+6.0%) in 30d · Committed yesterday · Python · Other license
Shares Evaluation & Guardrails, Observability & Tracing
eBPF Information Flow Enforcement for AI Agent safety, security and effectiveness
+6 (+5.7%) in 30d · Committed yesterday · C · MIT
Shares Observability & Tracing, Evaluation & Guardrails
Security-oriented three-axis observability for sandboxed AI agents: model intent, app context, and runtime…
+6 (+10%) in 30d · Committed 2d ago · Go · Apache-2.0
Shares Observability & Tracing, Evaluation & Guardrails
AI agent supervision framework in alpha. Decide MCP tool calls by policy and check recorded runs…
-1 (-7.7%) in 30d · Committed today · Go · Apache-2.0
Shares Evaluation & Guardrails, Observability & Tracing
- Language
- Go
- License
- Apache License 2.0
- Contributors
- 6
- Forks
- 129
- Watchers
- 9
- Open issues
- 8
- Releases
- 4
- Created
- 2026-07-24
- Stars this week
- +13
You've seen where numbat stands today.
Get the moves before everyone else: the 5 Observability & Tracing repos climbing fastest, every Tuesday.
Free weekly digest. Double opt-in, unsubscribe anytime.