Radar / AI infrastructure / LiteLLM Lens
LiteLLM Lens — AI agents that analyze agent traces inside the gateway
Trace-analysis product using AI agents to find recurring failures across agent runs: send OpenTelemetry traces to the LiteLLM proxy; Lens analyzes runs against team-defined criteria, groups similar issues, and links back to traces. Early access via waitlist.
Why it matters
Turns the gateway from model-traffic routing into the agent-debugging chokepoint — traces analyzed where model calls already flow, without a separate hosted observability service; self-hosted (traces in ClickHouse, results in Postgres).
What you could build with it
An infra team can attach failure-clustering trace analysis to any LLM proxy they run to auto-generate agent incident runbooks; security teams get agent-behavior inspection without exporting trace data.
Does it hold up?
Too early to judge — early access via waitlist; no independent usage data yet.
Built with LiteLLM Lens
- LiteLLM Lens: agent trace analysis launchruntimewire · Based on co-founder/CTO Ishaan Jaffer's launch thread: AI agents find recurring failures across agent runs against team-defined criteria; customer-deployed with analyzer calls routed through the proxy.
Learn more
First spotted on article: source.
More AI infrastructure
Modular open-sources MAX inference server, Mojo stdlib and accelerator kernelsThe core of Modular's unified AI deployment stack is now open: the MAX inference server (OpenAI-compatible endpoints)…infra · JEV 0.76OmniRouteFree MIT AI gateway: one endpoint, 290+ providers and 500+ models with quota-aware auto-fallback.infra · JEV 0.75Cloudflare Agents Week: Sandboxes GA, 50K concurrent Workflows, Managed OAuth for agentsA dozen agent-infrastructure launches in one week: persistent Linux Sandboxes (GA) with real shell/filesystem/state…infra · JEV 0.69ai-memory: long-term memory for agent coding CLIsRust solution for long-term memory for agent coding CLIs, facilitating handoff between different agents and sessions.infra · JEV 0.68DeepSeek open-sources Ascend infrastructure stackDeepSeek published Ascend-optimized versions of its NVIDIA-proven infra components — TileLang Ascend, DeepGEMM-Ascend…infra · JEV 0.65Hindsight: agent memory that learnsAgent memory system built for learning over time: retain/recall/reflect operations with SOTA scores on the LongMemEval…infra · JEV 0.63
Get the week's best AI launches, plus 3 ideas worth building
One email every Saturday. Ranked by traction, not hype. Free.