ContextFS

What it does

ContextFS gives Claude Code a second brain. Run contextfs build once and every source file gets a plain-text summary. From then on, Claude reads ~13,000 tokens instead of ~69,000 — that's 81% fewer tokens per file. When you close a session, ContextFS auto-compacts it into decisions, open questions, and next steps. Open a new session and Claude Code picks up exactly where you left off. Less context. Less tokens. Less money.

• 
  Diet Claude13d ago · dietclaude.com · ▲423

  Diet Claude — a usage meter for Claude that drains as you go and refills when your session resets. Crack open the can — free on the Chrome Web Store.

• CA
  CodeBurn – Analyze Claude Code token usage by taskApr 2026 · github.com · ▲112

  Built this after realizing I was spending ~$1400/week on Claude Code with almost no visibility into what was actually consuming tokens. Tools like ccusage give a cost breakdown per model and per day, but I wanted to understand usage at the task level. CodeBurn reads the JSONL session transcripts that Claude Code stores locally (~/.claude/projects/) and classifies each turn into 13 categories based on tool usage patterns (no LLM calls involved). One surprising result: about 56% of my spend was on conversation turns with no tool usage. Actual coding (edits/writes) was…

• 
  Context GatewayMar 2026 · github.com · ▲220

  Make Claude Code faster and cheaper without losing context

• CM
  Context Mode – 315 KB of MCP output becomes 5.4 KB in Claude CodeFeb 2026 · github.com · ▲84

  Every MCP tool call dumps raw data into Claude Code's 200K context window. A Playwright snapshot costs 56 KB, 20 GitHub issues cost 59 KB. After 30 minutes, 40% of your context is gone. I built an MCP server that sits between Claude Code and these outputs. It processes them in sandboxes and only returns summaries. 315 KB becomes 5.4 KB. It supports 10 language runtimes, SQLite FTS5 with BM25 ranking for search, and batch execution. Session time before slowdown goes from ~30 min to ~3 hours. MIT licensed, single command install: /plugin marketplace add mksglu/claude-context-mode…

• IU
  I used Claude Code to discover connections between 100 booksJan 2026 · trails.pieterma.es · ▲524

  I 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…

• 
  Bench for Claude CodeMar 2026 · bench.silverstream.ai · ▲411

  Store, review, and share your Claude Code sessions

• 
  I trained a 125M model to autocomplete piano on-device▲598

  I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.

  AI · 17d ago · simedw.com

• 
  Astute▲585

  Automate your B2B brand going viral, with new media creators

  AI · 19d ago · company-app.joinastute.com

• 
  Grok Bot▲547

  AI teammates that you can give real work to

  AI · 26d ago · x.ai

• 
  Needle2: 14MB agentic LLM for phones, wearables, smart home and robots▲537

  Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…

  AI · 27d ago · cactuscompute.com

• 
  Monid▲475

  One wallet, every paid tool your agent needs

  AI · 7d ago · monid.ai

• 
  Clara AI SDR▲460

  Turn website visitors into qualified pipeline

  AI · 20d ago · clarasdr.ai

• 
  Brew ▲905

  Like Claude design for email marketing

  AI · May 2026 · brew.new

• 
  Kilo Code for VS Code▲897

  Parallel agents, diff reviewer, and multi-model comparisons

  Dev tools · May 2026 · kilo.ai

• 
  StoreClaw▲805

  Grow your store profits with agents that know how to sell

  AI · May 2026 · storeclaw.ai

• 
  PollyReach▲796

  Give your agent a real number and voice to make calls.

  AI · May 2026 · pollyreach.ai

• NW
  Needle: We Distilled Gemini Tool Calling into a 26M Model▲776

  Hey HN, Henry here from Cactus. We open-sourced Needle, a 26M parameter function-calling (tool use) model. It runs at 6000 tok/s prefill and 1200 tok/s decode on consumer devices. We were always frustrated by the little effort made towards building agentic models that run on budget phones, so we conducted investigations that led to an observation: agentic experiences are built upon tool calling, and massive models are overkill for it. Tool calling is fundamentally retrieval-and-assembly (match query to tool name, extract argument values, emit JSON), not reasoning. Cross-attention…

  Life & fun · May 2026 · github.com

• FM
  Files.md – Open-source alternative to Obsidian▲730

  Dev tools · May 2026 · github.com