agent-lens: Agent observability and replay tooling for AI safety & interpretability research

by dreadnode · Agent Tool · ★ 118

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

Security audit verdict: SAFE · quality 78/100

None of the 44 rules matched — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against 44 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours.

The quality score combines nine heuristic checks of the repo and its README: completeness, clarity, specificity, examples, structure, agent readiness, step-by-step content, instruction quality and security notes. It rates how well the project explains itself to an agent, not the code.

aialignmentinterpretabilityobservabilitysafety

Quick Facts

Stars118
Forks10
LanguagePython
CategoryAgent Tool
LicenseMIT
Quality Score78/100
Open Issues3
Last Updated2026-06-19
Created2026-03-18
Platformspython
Est. Tokens~20k

About agent-lens

AgentLens Developed at MATS Exploration Phase under Neel Nanda, for a research project with Greg Kocher. A harness for running multi-session agent trajectories using the Claude Agent SDK, capturing them in ATIF (Agent Trajectory Interchange Format), and tracking file state changes across sessions.

Compatible Skills

These tools work well together with agent-lens for enhanced workflows:

  • agent-trace — semantic(0.30)+complementary+same_lang+similar_pop+shared_platform (55%)

agent-lens alternative? Top 6 similar tools

Looking for a agent-lens alternative? If you're comparing agent-lens with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • claude-warden by johnzfitch · ⭐ 60

    Security hooks and monitoring for Claude Code — quiet overrides, SSRF protection, MCP compression, OTEL tracin

  • ai-observer by tobilg · ⭐ 283

    Unified local observability for AI coding assistants

  • J-Wash by Extraltodeus · ⭐ 242

    Jacobian-Brainwash : A manual alignment tool for large language models built on Anthropic's Jacobian Lens. Res

  • dynolab by canivel · ⭐ 235

    Dyno Lab — an AI safety, alignment and interpretability research workbench for Apple Silicon. Explore activati

  • argus by yessGlory17 · ⭐ 119

    Claude Code Agent Monitoring & Observability on VSCode

  • mcpcat-typescript-sdk by MCPCat · ⭐ 103

    MCPcat is an analytics platform for MCP server owners 🐱.

More Agent Tool Tools

Explore other popular agent tool tools:

View all Agent Tool tools →

Popular Python Agent Tools

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 44 published rules, covering credential harvesting, data exfiltration, curl | sh installers and more. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

View on GitHub → Browse Agent Tool tools