maki

1. claude-code

   Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflows - all through natural language commands.

   

2. AppSignal

   www.appsignal.com sponsored

   AppSignal knows why the f*#k it crashed. Stop vibe-debugging. Every exception, every backtrace, grouped so you see patterns, not noise.

   

3. 

4. 

5. rtk

   CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies

   

6. pi-mono

   Discontinued AI agent toolkit: coding agent CLI, unified LLM API, TUI & web UI libraries, Slack bot, vLLM pods [Moved to: https://github.com/earendil-works/pi]

   

7. piclaw

   pi coding agent in a technicolor web trenchcoat

   

8. caveman

   🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman

   

9. SaaSHub

   www.saashub.com sponsored

   SaaSHub - Software Alternatives and Reviews. SaaSHub helps you find the best software and product alternatives

   

10. oh-my-pi

    ⌥ AI Coding agent for the terminal — hash-anchored edits, optimized tool harness, LSP, Python, browser, subagents, and more

    

11. headroom

    Discontinued Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 60-95% fewer tokens, same answers. Library, proxy, MCP server. [Moved to: https://github.com/headroomlabs-ai/headroom] (by chopratejas)

    

12. pi

    AI agent toolkit: coding agent CLI, unified LLM API, TUI & web UI libraries, Slack bot, vLLM pods

    

13. tweakcc

    Customize Claude Code's system prompts, create custom toolsets, input pattern highlighters, themes/thinking verbs/spinners, customize input box & user message styling, support AGENTS.md, unlock private/unreleased features, and much more. Supports both native/npm installs on all platforms.

    

14. forgecode

    AI enabled pair programmer for Claude, GPT, O Series, Grok, Deepseek, Gemini and 300+ models

    

15. pi-sandbox

    OS-level sandboxing for pi with interactive permission prompts

    

16. codebase-memory-mcp

    High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds. 158 languages, sub-ms queries, 99% fewer tokens. Single static binary, zero dependencies.

    

17. tilth

    Smart(er) code reading for humans and AI agents. Reduces cost per correct answer by ~40% on average. Install: cargo install tilth -or- npx tilth

    

18. claude-code-system-prompts

    All parts of Claude Code's system prompt, 27 builtin tool descriptions, sub agent prompts (Plan/Explore/Task), utility prompts (CLAUDE.md, compact, statusline, magic docs, WebFetch, Bash cmd, security review, agent creation). Updated for each Claude Code version.

    

19. moarcode

    You design, Claude writes, Codex reviews, and Gemini doesn't get installed

    

20. aipack

    Run, Build, Share your AI Packs

    

21. hax

    A minimalist, terminal-native coding agent written in C. (by OleksandrChekhovskyi)

    

22. i-have-adhd

    Claude Code skill to stop it from burying the answer. ADHD-friendly output.

    

23. SaaSHub

    www.saashub.com sponsored

    SaaSHub - Software Alternatives and Reviews. SaaSHub helps you find the best software and product alternatives

    

NOTE: The number of mentions on this list indicates mentions on common posts plus user suggested alternatives. Hence, a higher number means a better maki alternative or higher similarity.

maki discussion

maki reviews and mentions

Posts with mentions or reviews of maki. We have used some of these posts to build our list of alternatives and similar projects. The last one was on 2026-08-19.

• Anthropic Refuses to Support Agents.md
• fx :Tiny, open, native coding agent.

  Since I've seen some other agent tools being suggested, let me throw Maki in the ring as well: https://maki.sh/

  - written in rust, super fast startup and rendering

• Why does Opus 5 feel worse to work with?
• GLM-5.3: Frontier Coding with Emergent Cyber Capabilities
• Launch HN: Bullet (YC S26) – A Faster Coding Agent

  Are you freaking kidding me with YC throwing money at something like this? I guess I can fund raise just by having built https://maki.sh, and months ahead of other founders too...

• Stateless MCP has recaptured my interest

  That's a harness concern, not a protocol concern. For example, maki [0] allows that automatically for all tools

  > code_execution tool - uses monty to run an interpreter that has all other tools available as async functions. Maki uses it to filter / summarize / transform / pipe data to other tools as input, without it ever reaching and polluting the context window. Sandbox limited by time & memory.

  Failing that, you can just disable native MCP in your harness and have your agent use a CLI tool that calls MCP, like mcp-cli [1], and then the agent can use regular unix pipes to filter or transform the output. Here, rather than raw grep or sed (which are line oriented), the agent would probably use things like jq.

  [0] https://github.com/tontinton/maki#context-efficiency

  [1] https://github.com/philschmid/mcp-cli

• Pi's Minimalism Is Its Advantage

  I personally also don't like this, so use cargo to install it, it's in the readme. Takes a reasonable time to build on my X220, but on a modern computer it is plenty fast.

    cargo install --locked --git https://github.com/tontinton/maki.git maki

• Migrate from OpenClaw

  This is a genuinely interesting project. Thanks for sharing it for what its worth, I think it fits my definition of minimalist for the most part.

  Do you have anything for pi in general as well? I have currently tried out oh-my-pi and (well previously opencode) and I know about https://zot.sh for something completely in golang and also https://maki.sh/ both of which are created by another HN user.

  I have found projects created by frequent HN users (in terms of how much they interact with the site) to be genuinely useful/interesting within this space as compared to complete hype. I might bet there to be a very significant overlap and thus, it might be a good filter for these AI projects.

  Now aside from this one of the things that I want is I have found opencode + obra/superpowers to be a bit token intensive but its much more hands driven development and the AI doesn't completely go amok. I basically just want to replicate something like this either in pi or rust/golang alternative of it as well and then to use it completely with mobile phone as a means of interaction using say matrix protocol. (Optionally: I have glm 5.2 previous coding subscription where the rate limits is actually 5 hour rolling window rather than weekly so I would like to make it re-run/continue automatically after the 5 hour window on a project just continously to build on the side to use those tokens and just building something in an AFK fashion.)

  This might be my ideal workflow, Given that Pi is extensible, I think that Opencrow/your fork of it can be useful in one of the pieces of this ideal workflow. I'd be genuinely curious as it wasn't until quite recently that I went from my minimalist model of defaults to customizations/skills.md and I am just dabbling on different levels of complexity to find out what makes the right sense of having complexity towards on.

• The Token Compression Illusion: Why I'm Skeptical of RTK

  > what’s the real pitch on why

  I’m not OP, but parent comment and linked site https://maki.sh talk about token reduction.

• Show HN: Semble – Code search for agents that uses 98% fewer tokens than grep

  I also like the index feature form https://maki.sh

• A note from our sponsor - AppSignal

  www.appsignal.com | 26 Aug 2026

  Stop vibe-debugging. Every exception, every backtrace, grouped so you see patterns, not noise. Learn more →

tontinton/maki is an open source project licensed under MIT License which is an OSI approved license.

The primary programming language of maki is Rust.