CodeRLM – Tree-sitter-backed code indexing for LLM agents
I've been building a tool that changes how LLM coding agents explore codebases, and I wanted to share it along with some early observations. Typically claude code globs directories, greps for patterns, and reads files with minimal guidance. It works in kind of the same way you'd learn to navigate a city by walking every street. You'll eventually build a mental map, but claude never does - at least not any that persists across different contexts. The Recursive Language Models paper from Zhang, Kraska, and Khattab at MIT CSAIL introduced a cleaner framing. Instead of cramming everything into…
CodeRLM – Tree-sitter-backed code indexing for LLM agents launched on February 11, 2026 with 81 votes, #476 of 16,628 launches that month and more than 95% of that year's launches.
In plain words
CodeRLM is a code indexing tool that helps LLM coding agents navigate and understand large codebases more efficiently. It uses tree-sitter to parse code and build a searchable symbol table with cross-references, letting AI agents query only the information they need rather than reading files blindly. Built as a Rust server with an API backend, it's designed for developers who want their LLM agents to work with code systematically, drilling deeper into specific areas on demand instead of exhausting context by exploring everything at once.
written from the facts on this page · September 2026
From the sources
Tree-sitter-powered code indexing server that gives LLM agents precise, on-demand access to symbols, implementations, callers, tests, and grep across multi-language projects - so they explore codebases through targeted queries instead of loading everything into context. - coderlm/server/REPL_to_API.md at main · JaredStewart/coderlm
In the maker’s words, at launch
I've been building a tool that changes how LLM coding agents explore codebases, and I wanted to share it along with some early observations. Typically claude code globs directories, greps for patterns, and reads files with minimal guidance. It works in kind of the same way you'd learn to navigate a city by walking…
Does a similar job
all alternatives →
I used Claude Code to discover connections between 100 booksJan 2026 · trails.pieterma.es · ▲524I think LLMs are overused to summarise and underused to help us read deeper. I built a system for Claude Code to browse 100 non-fiction books and find interesting connections between them. I started out with a pipeline in stages, chaining together LLM calls to build up a context of the library. I was mainly getting back the insight that I was baking into the prompts, and the results weren't particularly surprising. On a whim, I gave CC access to my debug CLI tools and found that it wiped the floor with that approach. It gave actually interesting results and required very little orchestration…
Context GatewayMar 2026 · github.com · ▲220We built an open-source proxy that sits between coding agents (Claude Code, OpenClaw, etc.) and the LLM, compressing tool outputs before they enter the context window. Demo: https://www.youtube.com/watch?v=-vFZ6MPrwjw#t=9s. Motivation: Agents are terrible at managing context. A single file read or grep can dump thousands of tokens into the window, most of it noise. This isn't just expensive — it actively degrades quality. Long-context benchmarks consistently show steep accuracy drops as context grows (OpenAI's GPT-5.4 eval goes from 97.2% at 32k to 36.6% at 1M…
Semble – Code search for agents that uses 98% fewer tokens than grepMay 2026 · github.com · ▲445Hey HN! We (Stephan and Thomas) recently open-sourced Semble. We kept running into the same problem while using Claude Code on large codebases: when the agent can't find something directly, it falls back to grep, reading full files or launching subagents. This uses a lot of tokens, and often still misses the relevant code. There are existing tools for this, but they were either too slow to index on demand, needed API keys, or had poor retrieval quality. Semble is our solution for this. It combines static Model2Vec embeddings (using our latest static model: potion-code-16M) with BM25, fused…
I ported Tree-sitter to GoFeb 2026 · github.com · ▲222This started as a hard requirement for my TUI-based editor application, it ended up going in a few different directions. A suite of tools that help with semantic code entities: https://github.com/odvcencio/gts-suite A next-gen version control system called Got: https://github.com/odvcencio/got I think this has some pretty big potential! I think there's many classes of application (particularly legacy architecture) that can benefit from these kinds of analysis tooling. My next post will be about composing all these together, an exciting project I call…
Bloop – Answer questions about your code with an LLM agent2023 · github.com · ▲118Hi HN! We launched bloop 10 weeks ago (https://news.ycombinator.com/item?id=35236275) and received a huge amount of feedback (both positive + constructive). We've undertaken a rewrite of the core search framework, which now acts as an LLM agent, significantly improving the number of queries that can be successfully answered. There's a bunch of hype surrounding LLM agents, but we're positive this is one of the first implementations of an agent that can deliver immediate value for engineers working on existing projects, especially larger ones. We'll do a full write up of how the…
A context-aware permission guard for Claude CodeMar 2026 · github.com · ▲127We needed something like --dangerously-skip-permissions that doesn’t nuke your untracked files, exfiltrate your keys, or install malware. Claude Code's permission system is allow-or-deny per tool, but that doesn’t really scale. Deleting some files is fine sometimes. And git checkout is sometimes not fine. Even when you curate permissions, 200 IQ Opus can find a way around it. Maintaining a deny list is a fool's errand. nah is a PreToolUse hook that classifies every tool call by what it actually does, using a deterministic classifier that runs in milliseconds. It maps commands to action types…
More ai this month
the category →
Paintings by AI models: programs run through a simulation of oil paint.
AI · 20d ago · stillwet.art
PixVerse R2▲381A real-time world model you can explore and change
AI · 28d ago · world.pixverse.video
Source: Show HN post ↗ · launch text quoted in part
Launched alongside, February 2026
the whole month →
Lovon AI Therapy▲801Feel closer and have more fun with your partner every day!
AI · Feb 2026 · lovon.app
Hello my name is Ben Ward for the past 3 years I have been remastering the financial game Wall Street Raider created by Michael Jenkins originally on DOS in 1986. It has been a rough journey but I finally see the light at the end of the tunnel. I just recently redid the website and thought maybe the full story of how this project came to be would interest you all. Thank you for reading.
Work · Feb 2026 · wallstreetraider.com