LogoThread Easy
  • 탐색
  • 스레드 작성
LogoThread Easy

트위터 스레드의 올인원 파트너

© 2025 Thread Easy All Rights Reserved.

탐색

Newest first — browse tweet threads

Keep on to blur preview images; turn off to show them clearly

I’m very pleased to introduce my latest tool for both humans and coding agents: the coding agent session search, or “cass” for short.

This tool solves a direct pain point I’ve been experiencing for months as a heavy user of coding agents, with tons of sessions across many tools (Claude Code, codex, cursor, and now gemini-cli) and projects: I’ll know that I talked about something, but be unable to find it or even remember where to try to look for it.

I wanted something instantly available in the terminal that would let me search in a rich way across ALL of those tools and sessions at once super fast, with basically no latency and true “search as you type” instant filtering and ranking/sorting.

And I wanted it to “just work” without configuration, to automatically find and use all my installed coding tools, even ones that I don’t currently use but might in the future (like opencode, aider, and others).

So I made cass in super high-performance rust with every optimization I could think of, and a huge amount of attention to ergonomics and user experience. I’m very pleased with how it came out and think you will be, too:

https://t.co/DXrvxsjTKy

But just as my recent bv tool is now being used way more by my agents than by me, I knew from the start that cass should have a “robot mode” designed specifically for use by coding agents. 

This tool gives coding agents the ability to reach into their own working notes and those of all their peer agents across tools. It’s like a human developer being able to search their Gmail, their notes, and their company Slack and Jira to find things. 

I went through countless iterations of improving the tool so that agents really love to use it. You can just add this blurb to your AGENTS dot md file to get them to use it (after doing the one-liner curl install, which takes 
3 seconds):

```
🔎 cass — Search All Your Agent History

 What: cass indexes conversations from Claude Code, Codex, Cursor, Gemini, Aider, ChatGPT, and more into a unified, searchable index. Before solving a problem from scratch, check if any agent already solved something similar.

 ⚠️ NEVER run bare cass — it launches an interactive TUI. Always use --robot or --json.

 Quick Start

 # Check if index is healthy (exit 0=ok, 1=run index first)
 cass health

 # Search across all agent histories
 cass search "authentication error" --robot --limit 5

 # View a specific result (from search output)
 cass view /path/to/session.jsonl -n 42 --json

 # Expand context around a line
 cass expand /path/to/session.jsonl -n 42 -C 3 --json

 # Learn the full API
 cass capabilities --json # Feature discovery
 cass robot-docs guide # LLM-optimized docs

 Why Use It

 - Cross-agent knowledge: Find solutions from Codex when using Claude, or vice versa
 - Forgiving syntax: Typos and wrong flags are auto-corrected with teaching notes
 - Token-efficient: --fields minimal returns only essential data

 Key Flags

 | Flag | Purpose |
 |------------------|--------------------------------------------------------|
 | --robot / --json | Machine-readable JSON output (required!) |
 | --fields minimal | Reduce payload: source_path, line_number, agent only |
 | --limit N | Cap result count |
 | --agent NAME | Filter to specific agent (claude, codex, cursor, etc.) |
 | --days N | Limit to recent N days |

 stdout = data only, stderr = diagnostics. Exit 0 = success.
```

Making this tool was a real labor of love. Even though I did it all in less than a week, it took a lot of hours and a ridiculous number of tokens and agents. I heavily used all the workflows and tricks I’ve been posting about recently.

It’s a good response to all the snarky comments from people saying that my approach is overly complex and asking “where’s the results?” 

Let’s see them make a program like this in a year, let alone under a week! And this isn’t even the main thing I’ve been working on during that time! It’s one of like 10+ projects I’ve been pushing forward at the same time.

I’m very pleased to introduce my latest tool for both humans and coding agents: the coding agent session search, or “cass” for short. This tool solves a direct pain point I’ve been experiencing for months as a heavy user of coding agents, with tons of sessions across many tools (Claude Code, codex, cursor, and now gemini-cli) and projects: I’ll know that I talked about something, but be unable to find it or even remember where to try to look for it. I wanted something instantly available in the terminal that would let me search in a rich way across ALL of those tools and sessions at once super fast, with basically no latency and true “search as you type” instant filtering and ranking/sorting. And I wanted it to “just work” without configuration, to automatically find and use all my installed coding tools, even ones that I don’t currently use but might in the future (like opencode, aider, and others). So I made cass in super high-performance rust with every optimization I could think of, and a huge amount of attention to ergonomics and user experience. I’m very pleased with how it came out and think you will be, too: https://t.co/DXrvxsjTKy But just as my recent bv tool is now being used way more by my agents than by me, I knew from the start that cass should have a “robot mode” designed specifically for use by coding agents. This tool gives coding agents the ability to reach into their own working notes and those of all their peer agents across tools. It’s like a human developer being able to search their Gmail, their notes, and their company Slack and Jira to find things. I went through countless iterations of improving the tool so that agents really love to use it. You can just add this blurb to your AGENTS dot md file to get them to use it (after doing the one-liner curl install, which takes 3 seconds): ``` 🔎 cass — Search All Your Agent History What: cass indexes conversations from Claude Code, Codex, Cursor, Gemini, Aider, ChatGPT, and more into a unified, searchable index. Before solving a problem from scratch, check if any agent already solved something similar. ⚠️ NEVER run bare cass — it launches an interactive TUI. Always use --robot or --json. Quick Start # Check if index is healthy (exit 0=ok, 1=run index first) cass health # Search across all agent histories cass search "authentication error" --robot --limit 5 # View a specific result (from search output) cass view /path/to/session.jsonl -n 42 --json # Expand context around a line cass expand /path/to/session.jsonl -n 42 -C 3 --json # Learn the full API cass capabilities --json # Feature discovery cass robot-docs guide # LLM-optimized docs Why Use It - Cross-agent knowledge: Find solutions from Codex when using Claude, or vice versa - Forgiving syntax: Typos and wrong flags are auto-corrected with teaching notes - Token-efficient: --fields minimal returns only essential data Key Flags | Flag | Purpose | |------------------|--------------------------------------------------------| | --robot / --json | Machine-readable JSON output (required!) | | --fields minimal | Reduce payload: source_path, line_number, agent only | | --limit N | Cap result count | | --agent NAME | Filter to specific agent (claude, codex, cursor, etc.) | | --days N | Limit to recent N days | stdout = data only, stderr = diagnostics. Exit 0 = success. ``` Making this tool was a real labor of love. Even though I did it all in less than a week, it took a lot of hours and a ridiculous number of tokens and agents. I heavily used all the workflows and tricks I’ve been posting about recently. It’s a good response to all the snarky comments from people saying that my approach is overly complex and asking “where’s the results?” Let’s see them make a program like this in a year, let alone under a week! And this isn’t even the main thing I’ve been working on during that time! It’s one of like 10+ projects I’ve been pushing forward at the same time.

Here are just some of its many features. Why haven’t you installed it yet?! It’s FREE. And it’s FAST. Give yourself and your agent friends the gift of cass this holiday season.

avatar for Jeffrey Emanuel
Jeffrey Emanuel
Tue Dec 02 14:29:58
🎧 More morning walk thoughts — what we're working on now, and what I think I'm going to work on next.

🎧 More morning walk thoughts — what we're working on now, and what I think I'm going to work on next.

Creator of @tailwindcss. Listener of Slayer. Austin 3:16.

avatar for Adam Wathan
Adam Wathan
Tue Dec 02 14:29:04
October: $1.4 trillion in spending commitments.

November: Rough Vibes.

December: Code Red.

Life comes at you fast.

October: $1.4 trillion in spending commitments. November: Rough Vibes. December: Code Red. Life comes at you fast.

Managing Partner & CIO, @atreidesmgmt. Husband, @l3eckyy. No investment advice, views my own. https://t.co/pFe9KmNu9U

avatar for Gavin Baker
Gavin Baker
Tue Dec 02 14:28:45
a farm in Franklin, NC submitted this image for their job posting today, and the file name was 'GoatsGoneWild.jpg' 🤷♂️

a farm in Franklin, NC submitted this image for their job posting today, and the file name was 'GoatsGoneWild.jpg' 🤷♂️

they kept laying me off so I began building 🚜 🌱 https://t.co/wfrYC5S7wn 🧅 📦 https://t.co/JtMqAWilhs ecomm 🐂 🛠️ https://t.co/E8U0DUsKzT jobs 🟥 🟦 hottytoddy

avatar for Peter Askew
Peter Askew
Tue Dec 02 14:25:01
We tested the intelligent canvas workspace and the multi person collaboration flow inside Felo.
Used it in a real workflow. Uploaded a Git book, generated a summary, turned it into slides, added a cheat sheet, and expanded the deck. Another editor joined, added their own Git doc, and built a webpage from it.
All docs in one place, fully collaborative and grounded in real work.

🔗 https://t.co/EjIjEnKItx  |  @felo_ai_en

We tested the intelligent canvas workspace and the multi person collaboration flow inside Felo. Used it in a real workflow. Uploaded a Git book, generated a summary, turned it into slides, added a cheat sheet, and expanded the deck. Another editor joined, added their own Git doc, and built a webpage from it. All docs in one place, fully collaborative and grounded in real work. 🔗 https://t.co/EjIjEnKItx | @felo_ai_en

We're sharing/showcasing best of @github projects/repos. Follow to stay in loop. Promoting Open-Source Contributions. UNOFFICIAL, but followed by github

avatar for GitHub Projects Community
GitHub Projects Community
Tue Dec 02 14:22:35
You can insert images, refine layouts, and adjust visuals directly inside the doc or slide without switching tools.
This keeps long running documentation work consistent and easier to manage.

You can insert images, refine layouts, and adjust visuals directly inside the doc or slide without switching tools. This keeps long running documentation work consistent and easier to manage.

We tested the intelligent canvas workspace and the multi person collaboration flow inside Felo. Used it in a real workflow. Uploaded a Git book, generated a summary, turned it into slides, added a cheat sheet, and expanded the deck. Another editor joined, added their own Git doc, and built a webpage from it. All docs in one place, fully collaborative and grounded in real work. 🔗 https://t.co/EjIjEnKItx | @felo_ai_en

avatar for GitHub Projects Community
GitHub Projects Community
Tue Dec 02 14:22:16
  • Previous
  • 1
  • More pages
  • 1807
  • 1808
  • 1809
  • More pages
  • 5634
  • Next