Try-Works: An Index of Projects Referencing Recursive Language Models
By
handfuloflight
Summary
This is a brief project/product index entry for "Try-Works" that references the MIT paper on Recursive Language Models, which demonstrated a method for increasing effective context length to 10M tokens using sub-agents. The content notes there have been various implementations of this concept in development workflows, with some approaches storing entire contexts externally. The page appears to be a skill/package installation reference for a GitHub repository called "rlm-workflow" by user doubleuuser, with installation instructions via npx and skills.sh.
Source
Hacker NewsTry-Works: An Index of Projects Referencing Recursive Language Modelstry.worksKey quotes
· 3 pulledAfter the MIT paper Recursive Language Models paper demonstrated a method of increasing effective context length to 10M tokens by using sub-agents to move information from the context window to an information store outside the chat
There's been a number of different takes on how to put this into practice in development workflows.
Some even go in the direction of storing entire
You might also wanna read
Loop Library: An Open-Source Catalog and AI Skill for Reusable Agent Workflows
Loop Library is an open-source GitHub repository containing two components: a public website catalog where users and AI agents can browse, r
github.com·15d ago
Loop Library: A Technical Guide to Repeatable AI Agent Workflows and Agentic Engineering Loops
This article presents a comprehensive library of repeatable AI agent workflows called "Loop Library," focusing on agentic engineering loops.
signals.forwardfuture.com·5d ago
FastContext-1.0: A Lightweight Repository-Exploration Subagent for LLM Coding Agents
FastContext-1.0 is a lightweight repository-exploration subagent designed for LLM coding agents. It separates the roles of repository explor
Benchmarking GLM-5.2 vs Opus 4.8: Long-context retrieval performance for coding agents
This article benchmarks GLM-5.2 (an open-source model from Z.ai) against Anthropic's Opus 4.8 for long-context retrieval in coding agent use
braintrust.dev·7d ago
Context Management Strategies for OpenWork: A Complete Guide to the Desktop AI Agent Framework
Comments
Sign in to join the conversation.
No comments yet. Be the first.