Skip to content
View morluto's full-sized avatar

Highlights

  • Pro

Block or report morluto

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
morluto/README.md

Hey, I'm Morluto

X @morluto

I write about papers and books I'm reading, and things I'm building, on my blog here.

Reach me on X

Building

  • REA: Reverse Engineer Anything GitHub stars - One CLI and MCP server that lets coding agents inspect any app, understand how it works down to the binary level, and recreate features for your own product.
  • Preference - Research-driven data infrastructure for trading agents.
  • LeanToken GitHub stars - CLI + MCP to cut token costs for coding agents through context engineering. Indexes your code so agents see only what they need.
  • GitContribute GitHub stars - Local-first research workbench for discovering, investigating, and preparing focused GitHub contributions with evidence.

Contributing to

  • gstack GitHub stars - #1 outside contributor; project-local /browse install hardening and setup fixes.
  • Model Context Protocol GitHub stars - TypeScript SDK packaging fix for CommonJS validator exports and Ajv.
  • RepoPrompt GitHub stars - Context Builder model selection, agent-mode and tool-card reliability, workspace model drift cleanup, test harness hardening against hangs and waiter leaks, and hosted-app/XCTest sharding.
  • DeepSeek Agents GitHub stars - DeepSeek integration guides.
  • Flash Linear Attention GitHub stars - Split attention decode output offset fix.
  • Qwen Code GitHub stars - Config validation for fractional session and tool-call limits, max-token continuation rollback, MCP read-only auto-approval trust enforcement, and malformed tool result display resilience.
  • Hermes GitHub stars - Cron scheduler double-execution prevention and credential-pool failover fix for provider auto-detection.
  • x-JEPA GitHub stars - Correctness fixes across the JEPA training and planning stack: Wasserstein midpoint targets, unimodal Beta policies, goal/state token alignment, SIGReg dtype handling, and discrete planning action indices.
  • OpenClaw GitHub stars - Shared phone identity canonicalization, Signal/iMessage routing fixes, WhatsApp normalization coverage, stale-chunk recovery unblock, subagent registry resurrection prevention, and heartbeat responsiveness with large commitment queues.
  • Mooncake GitHub stars - RDMA completion resource validation, cross-thread SHM relocation mapping lifecycle, and NVMe-oF task batch rejection with cuFile completion correlation.
  • Vibe-Trading GitHub stars - Codex OAuth init/default-model fixes and CLI resume prompt input preservation.
  • Magpie GitHub stars - Fallible JSON parsing across FFI, runtime, codegen, semantic analysis, and web lowering.
  • gitcrawl GitHub stars - Portable store worktree verification to prevent local database misclassification under stray Git metadata.
  • UniRL GitHub stars - Sampling fix to make omitted autoregressive top-k unrestricted.
  • HarnessGym GitHub stars - Benchmark correctness fixes for result parsing, activation reporting, and artifact quarantine.

Pinned Loading

  1. rea rea Public

    Reverse engineer anything with agents: one CLI and MCP server to inspect any app, understand it fully down to the binary level.

    TypeScript 124 17

  2. garrytan/gstack garrytan/gstack Public

    Use Garry Tan's exact Claude Code setup: 23 opinionated tools that serve as CEO, Designer, Eng Manager, Release Manager, Doc Engineer, and QA

    TypeScript 122k 18.3k

  3. lucidrains/x-jepa lucidrains/x-jepa Public

    Explorations into some of the approaches advocated by Yann LeCun, and just a more wholistic architecture (JEPA) in general

    Python 95 7

  4. patrick-toulme/harnessgym patrick-toulme/harnessgym Public

    Iterative agent harness improvement: run a coding agent on a hard task, generate the reusable tooling it was missing, qualify it, and replay fresh sessions with it activated. Works with Codex and C…

    Python 40 3

  5. deepseek-ai/awesome-deepseek-agent deepseek-ai/awesome-deepseek-agent Public

    4.7k 571

  6. magpie-lang/magpie magpie-lang/magpie Public

    Rust 54 3