khasky

joined 2 weeks ago
sorted by: new top controversial old
18
Someone built a visualization of what 1 million tokens actually looks like (www.1millioncontext.com)
 

I found One Million Tokens. Its rough scale:

1M tokens
~ 750K words
~ 3,000 pages
~ 83 hours of conversation
~ 75K lines of code

๐Ÿง  The more interesting part is the timeline.

It starts with GPT-3 at 2,048 tokens in 2020, then walks through ChatGPT 4K, GPT-4 32K, Claude 100K, Gemini 1M, and the later multi-million-token era.

The visual change is kind of absurd when you see all the pages stacked together.

One caveat: maximum context is not the same as perfect memory/retrieval. A model accepting 1M tokens can still fail to use information buried inside that window.

The line-of-code/page conversions are approximations too. I am curious how people here design around 1M+ context in practice.

Do you actually feed giant source sets directly, or still prefer retrieval + smaller focused contexts for cost/attention reasons?

-28
TeamAI puts your team's agent config behind a merge request (github.com)
 

A tilted photograph of a curved roller conveyor carrying boxes through a warehouse, set under the headline: Push a rule, get it reviewed, and everyone pulls it. The conveyor stands for the distribution step, where a merged change to the team's agent config is carried to every member's machine by a hook that runs when their next session starts.

Worth knowing before anyone installs Tencent's teamai-cli on the strength of its front page: the automatic half runs off a hook, and 3 of the 11 agents it lists have none. The rest of it I like.

Tencent has published teamai-cli, which treats that as distribution rather than discipline. One git repo holds skills/, rules/, hooks/hooks.yaml, mcp/mcp.yaml, agents/, docs/ and a culture.md that gets injected into each agent's CLAUDE.md or AGENTS.md. Install is npm install -g teamai-cli, then teamai init <repo-url> against a repo the team can write to.

The flow is the point: teamai push opens a branch and a merge request, a reviewer merges, and the next session's SessionStart hook runs teamai pull so the change lands in everyone's local tools. teamai roles and teamai tags mean nobody is forced to sync skills they do not use.

I counted what it promises per agent before getting interested, since that is what decides whether it reaches your machine. Skills and docs are filled on all 11 agents in the table, hooks and MCP on 8. The automatic pull is itself a hook, so on OpenClaw, Hermes and DeepSeek Harness my read is that you are pulling by hand.

Worth knowing: the shared env/ resource explicitly is not for secrets, and the recall and dashboard halves are both marked beta. Repo: https://github.com/Tencent/teamai-cli

Has a rule ever landed in your shared setup that you would have blocked if you had seen the diff first?

-73
I found a portable AI coding agent that solves a boring but real problem (github.com)
 

๐Ÿ’ป I came across OpenClaude-Portable and I like the idea mostly because it reduces repeated setup.

It packages an AI coding agent into a self-contained folder and supports 9 providers, including Claude, OpenAI, Gemini, Ollama and LM Studio.

Settings, API keys and sessions stay inside the project directory.

Cloud providers still need internet, but with Ollama or another local provider the coding workflow can stay local once configured.

It supports Windows, Linux and macOS. ๐Ÿ’พ

To me, the interesting part is not "coding from a flash drive". It is being able to move the whole agent environment between machines.

Has anyone here tried doing this from a USB SSD in a real workflow?