Research framework of diagnostic guardrails that analyse full agent trajectories to flag unsafe actions and attacks.
Last verified Nov 2026 against its GitHub repository
Showing 1–13 of 13 · A to Z
Research framework of diagnostic guardrails that analyse full agent trajectories to flag unsafe actions and attacks.
Last verified Nov 2026 against its GitHub repository
Trace, debug and deploy reliable AI agents with time-travel debugging and cost tracking.
Last verified: Nov 2026
Local-first Rust TUI and CLI for auditing AI coding-agent sessions: cost, tokens, latency, failures and health.
Last verified Nov 2026 against its GitHub repository
Deterministic pre-action authorization that checks agent tool calls against policy before they run.
Last verified Nov 2026 against its GitHub repository
Agent observability and evaluation platform, including the open-source Phoenix tracing and eval tool.
Last verified: Nov 2026
AI observability platform for tracing production agents, running evals and catching regressions.
Last verified: Nov 2026
AI gateway and LLM observability for routing and monitoring reliable AI apps.
Last verified: Nov 2026
AI-native security platform for GenAI, backed by a large AI red team.
Last verified: Nov 2026
Open-source LLM engineering platform for agent tracing, evals, prompt management and metrics.
Last verified: Nov 2026
LangChain's platform for tracing, debugging, evaluating and monitoring LLM apps and agents, usable with or without LangChain.
Last verified: Nov 2026
Open-source end-to-end AI observability platform from Comet for testing and improving agentic systems.
Last verified: Nov 2026
AI security platform that catches vulnerabilities in agents during development, used by 300,000+ developers.
Last verified: Nov 2026
Observability and continuous improvement for production agents from Weights & Biases.
Last verified: Nov 2026