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?

I went through the Edge0 repo after the clip of a 35B model on an iPhone, and I want to check my reading with people who actually run local models. No affiliation, just curious.

Edge0 (Edge0-AI, Apache 2.0, released the other day) is a streaming inference engine with two preview MoE models, Edge0-35B-A3B on a Qwen3.5-MoE base and Edge0-8B-A1B on Ling 3.0. The mechanism is expert offload: the 4-bit checkpoint stays on the SSD, expert weights are mmapped, and only the routed experts (4 of 256 per token, about 3B active of 35B) get read per token. The project reports 2.9 GB peak for the 35B and 1.0 GB for the 8B at short context on a Mac mini M4 Pro, with decode at 14.9-17.7 and 23.9-25.3 tok/s. The 35B checkpoint is 19.6 GB on disk.

My reading, which is the part I want checked: 3B active at 4 bits is about 1.5 GB, and at 15 to 18 tok/s a cold read of that per token would need over 20 GB/s, so most expert reads must be hitting the OS file cache. That makes "peak active memory" the process's resident set, with the cached pages outside it, and a 24 GB mini has room to hide a lot of the checkpoint there.

What shipped is MLX on Apple Silicon Macs only, the iPhone is the demo video, and I could not find the "iPhone 15 Pro and newer" floor on any primary page 🧐 Repo: https://github.com/Edge0-AI/edge0/

For anyone who has tried it on a Mac with less memory than that mini: does the 2.9 GB peak hold once the KV cache grows past a few thousand tokens, or does it start swapping?

The project is an MoE-native serving engine that treats GPU, CPU, host RAM, and PCIe bandwidth as one inference platform. ⚡

Published paper results include:

Qwen3.6-35B-A3B
RTX 4060 Laptop 8GB
39.3 tok/s

DeepSeek-V4-Flash 284B
RTX 5090
22-25 tok/s

The full expert pool lives in system RAM and VRAM acts as an expert cache.

On cache misses, FreeToken can either transfer an expert to the GPU or execute it directly on the CPU, with the split chosen from measured bandwidth.

Important caveat: low VRAM does not mean low total memory. The host RAM still has to hold the expert weights.

https://github.com/FlashML-org/FreeToken

Current support is mainly x86_64 + NVIDIA RTX 30/40/50-series hardware.

Has anyone here benchmarked it against llama.cpp/Ollama on the same checkpoint and hardware? I would be interested in real-world agent workloads rather than short synthetic decode tests.

I think fal's recent H3 Max experiments are more interesting than the "AI slop" framing makes them sound.

H3 Max can reportedly generate a 5-second clip in under 3 seconds.

Fal engineer Rehan Sheikh used that speed to build an endless livestream inspired by interdimensional cable. After Twitch and Kick removed it, fal launched its own platform:

https://fal.live/

The channels are continuously generated, and viewers can influence what happens next.

Pieter Levels also built Infinite Slop with fal:

https://infiniteslop.ai/

It is exactly what the name implies, but the feedback loop is interesting: audience prompt -> generated scene -> audience response -> next scene. 📺

The technical release underneath this is H3 Max Director:

https://fal.ai/h3-max-director

Unlike normal clip generation, Director keeps an active realtime session and carries context across segments. Fal's docs say public sessions currently run up to 2 minutes.

Current promo pricing is $0.02 per generated second, which makes continuous generation about $1,728/day.

I am not convinced infinite AI TV itself is the killer app, but a stateful video stream that can be redirected while it plays seems like a genuinely new primitive.

What would you actually build with that?

Usage:

/eli5 <topic>

Claude creates an HTML artifact with big pictures and very few words.

Anthropic's Thariq Shihipar shared it and said people at Anthropic have been using it a lot recently.

The whole skill file is only 10 lines. 🧠

The useful idea is not really "talk to me like a child."

It is:

assume I am smart, but assume I know nothing about this topic yet.

That makes it a good first pass for things like DNS, virtual memory, backpropagation, economics, philosophy, etc.

I would still use proper docs/books/papers for the detailed layer.

Skill: https://github.com/anthropics/claude-plugins-community/tree/main/eli5

Has anyone here tried using this visual-first workflow for learning unfamiliar codebases?

💻 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. 💾

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?