Back to News
SuperagenticAIMay 3, 2026

RLM Code v0.1.8

Paid
LLM
Coding Agent
Open Source
Benchmarking
Research
REPL
Agent Harness

Explore RLM Code v0.1.8

Visit the official website to learn more and get started

### TL;DR

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.

Key Insights & Metrics

Pricing
Free (Open Source, Apache-2.0)
Cost structure
Version
v0.1.8
Current release version
Hardware
Python 3.11+, Docker recommended for sandboxed code execution
Compute requirements
Category
Paid
Licensing model
Region
Global
Primary region

Key Features

  • 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

Discussion

0
Upvotes
0
Downvotes
0 reviews

Sign in to leave a review

Reviews

No reviews yet. Be the first to review!

🚀 Join the AI dev community — follow us everywhere

© 2026 MARKTECHPOST AI MEDIA INC. All rights reserved.Terms & ConditionsPrivacy Policy
Beta Mode