RLM Code v0.1.8 vv0.1.8
RLM Code v0.1.8 is an open-source research playground for running LLM-powered coding agents in a recursive REPL loop, with benchmarking, trajectory replay, and OTel-based trace analysis for diagnosing agent harness failures.
New trace_analysis environment for diagnosing agent harness failures from OTel-shaped JSONL traces
AHE-style evidence corpus export with per-trace detail reports, index.json, and raw JSONL spans
Sidecar trace indexing with dataset overview, query, count, search, and full-trace view actions
PricingFree (Open Source, Apache-2.0)
Versionv0.1.8