No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by dreadnode · Agent Tool · ★ 111
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is agent-lens safe to install? View the security audit →
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. Built for AI alignment and interpretability research — studying how LLM agents behave across multi-turn, multi-session, multi-agent interactions. Note: AgentLens currently supports Claude Code via the Claude Agent SDK. Support for additional agents and frameworks is planned — see Roadmap. Some features (especially turn-level replay) are experimental. We welcome PRs and contributions — open an issue if you run into bugs.
| Stars | 111 |
| Forks | 11 |
| Language | Python |
| Category | Agent Tool |
| License | MIT |
| Quality Score | 78.3572886337165/100 |
| Open Issues | 2 |
| Last Updated | 2026-06-19 |
| Created | 2026-03-18 |
| Platforms | python |
| Est. Tokens | ~20k |
These tools work well together with agent-lens for enhanced workflows:
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.
Security hooks and monitoring for Claude Code — quiet overrides, SSRF protection, MCP compression, OTEL tracin
Unified local observability for AI coding assistants
Jacobian-Brainwash : A manual alignment tool for large language models built on Anthropic's Jacobian Lens. Res
Claude Code Agent Monitoring & Observability on VSCode
MCPcat is an analytics platform for MCP server owners 🐱.
Open-source AI copilot that lets you chat with your observability data and code 🧙♂️
Explore other popular agent tool tools:
agent-lens is Agent observability and replay tooling for AI safety & interpretability research.. It is categorized as a Agent Tool with 111 GitHub stars.
agent-lens is primarily written in Python. It covers topics such as ai, alignment, interpretability.
You can find installation instructions and usage details in the agent-lens GitHub repository at github.com/dreadnode/agent-lens. The project has 111 stars and 11 forks, indicating an active community.
agent-lens is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to agent-lens on Agent Skills Hub include claude-warden, ai-observer, J-Wash. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.