✋ Local models don't make you safe: your agent can read your env vars and your whole home directory.
Mini Me v1.0.5 brings mm dockerinit: a Dockerfile + compose.yaml, and the agent runs in a container, as a non-root user.
mini-me.org/p/20261107-m...
#Docker #LocalModels
Mini Me v1.0.5 brings mm dockerinit: a Dockerfile + compose.yaml, and the agent runs in a container, as a non-root user.
mini-me.org/p/20261107-m...
#Docker #LocalModels
Let's protect Mini Me, part 1: `mm dockerinit`
Your local agent can read your secrets and your whole home directory. See how mm dockerinit runs Mini Me in a container, as a non-root user, in one command.
mini-me.org
November 7, 2026 at 6:18 PM
✋ Local models don't make you safe: your agent can read your env vars and your whole home directory.
Mini Me v1.0.5 brings mm dockerinit: a Dockerfile + compose.yaml, and the agent runs in a container, as a non-root user.
mini-me.org/p/20261107-m...
#Docker #LocalModels
Mini Me v1.0.5 brings mm dockerinit: a Dockerfile + compose.yaml, and the agent runs in a container, as a non-root user.
mini-me.org/p/20261107-m...
#Docker #LocalModels
Part 2: Mini Me in a @docker.com sbx micro-VM, with mm sbxinit and one sbx env run.
The best bit: the agent uses your #Context7 API key but can't read it. It only sees a decoy, the sbx proxy swaps in the real key on the way out.
mini-me.org/p/20261108-m...
#sbx #LocalModels
The best bit: the agent uses your #Context7 API key but can't read it. It only sees a decoy, the sbx proxy swaps in the real key on the way out.
mini-me.org/p/20261108-m...
#sbx #LocalModels
Let's protect Mini Me, part 2: `mm sbxinit`
Run Mini Me in a Docker sbx micro-VM with mm sbxinit: an isolated sandbox, network policies, and secrets injected by the proxy so the agent never sees them.
mini-me.org
November 8, 2026 at 11:46 AM
Part 2: Mini Me in a @docker.com sbx micro-VM, with mm sbxinit and one sbx env run.
The best bit: the agent uses your #Context7 API key but can't read it. It only sees a decoy, the sbx proxy swaps in the real key on the way out.
mini-me.org/p/20261108-m...
#sbx #LocalModels
The best bit: the agent uses your #Context7 API key but can't read it. It only sees a decoy, the sbx proxy swaps in the real key on the way out.
mini-me.org/p/20261108-m...
#sbx #LocalModels
Sam Altman Absolutely Hates the Idea of People Running Their Own AI Models at Home, Argues They Shouldn't Own Computers futurism.com/artific... #AI #LocalModels #OpenAI #SurrenderYourRAM
November 1, 2026 at 1:36 PM
Sam Altman Absolutely Hates the Idea of People Running Their Own AI Models at Home, Argues They Shouldn't Own Computers futurism.com/artific... #AI #LocalModels #OpenAI #SurrenderYourRAM
I invited a Docker Agent into Sidekicks 🎉
Locutus, my local code agent, runs on a small model via @docker.com Model Runner. It can explore a project and run shell commands, and it asks before running tools.
sidekicks.world/p/20261103-a...
#DockerAgent #ACP #Sidekicks #LocalModels
Locutus, my local code agent, runs on a small model via @docker.com Model Runner. It can explore a project and run shell commands, and it asks before running tools.
sidekicks.world/p/20261103-a...
#DockerAgent #ACP #Sidekicks #LocalModels
Inviting Docker Agent into Sidekicks
Add a Docker Agent, powered by a small local model, to Sidekicks: configuration, the add-agent wizard, tool permissions, files, terminal, channels and settings.
sidekicks.world
November 3, 2026 at 3:42 AM
I invited a Docker Agent into Sidekicks 🎉
Locutus, my local code agent, runs on a small model via @docker.com Model Runner. It can explore a project and run shell commands, and it asks before running tools.
sidekicks.world/p/20261103-a...
#DockerAgent #ACP #Sidekicks #LocalModels
Locutus, my local code agent, runs on a small model via @docker.com Model Runner. It can explore a project and run shell commands, and it asks before running tools.
sidekicks.world/p/20261103-a...
#DockerAgent #ACP #Sidekicks #LocalModels
I wanted a Slack for my little local agents, not another CLI. So I built Sidekicks: channels, @ mentions, plain-words permissions, and any ACP agent (Claude, Codex...) plugged in, even in @docker.com sbx sandboxes.
sidekicks.world/p/20261102-s...
#AI #LocalModels #ACP
sidekicks.world/p/20261102-s...
#AI #LocalModels #ACP
Sidekicks: AI agents for citizen users/developers
Meet Sidekicks, a Slack-like desktop app where your local, containerized or ACP-compatible AI agents live in channels and answer in plain words.
sidekicks.world
November 2, 2026 at 7:20 AM
I wanted a Slack for my little local agents, not another CLI. So I built Sidekicks: channels, @ mentions, plain-words permissions, and any ACP agent (Claude, Codex...) plugged in, even in @docker.com sbx sandboxes.
sidekicks.world/p/20261102-s...
#AI #LocalModels #ACP
sidekicks.world/p/20261102-s...
#AI #LocalModels #ACP
Nothing forces an ACP client to be a code editor. Any program that can launch a process can drive Mini Me "as a library".
Node.js + the ACP SDK: stream answers, allow or refuse tools, cancel. No server, no port: two pipes.
mini-me.org/p/20261101-m...
#ACP #LocalModels
Node.js + the ACP SDK: stream answers, allow or refuse tools, cancel. No server, no port: two pipes.
mini-me.org/p/20261101-m...
#ACP #LocalModels
Using Mini Me as a library, thanks to ACP
Drive Mini Me from your own Node.js apps over ACP: ask questions, stream answers, allow or deny tools and cancel requests, with the official SDK and no server.
mini-me.org
November 1, 2026 at 9:33 AM
Nothing forces an ACP client to be a code editor. Any program that can launch a process can drive Mini Me "as a library".
Node.js + the ACP SDK: stream answers, allow or refuse tools, cancel. No server, no port: two pipes.
mini-me.org/p/20261101-m...
#ACP #LocalModels
Node.js + the ACP SDK: stream answers, allow or refuse tools, cancel. No server, no port: two pipes.
mini-me.org/p/20261101-m...
#ACP #LocalModels
One day, one feature, day 7: write your Mini Me tools in WASM.
Compiled with @tinygo.org , run by #wazero in a #wasm sandbox: only the folders you open, no env vars (so no secrets), no network. A 4B model gets four tools, nothing else.
mini-me.org/p/20261028-m...
#WASM #LocalModels
Compiled with @tinygo.org , run by #wazero in a #wasm sandbox: only the folders you open, no env vars (so no secrets), no network. A 4B model gets four tools, nothing else.
mini-me.org/p/20261028-m...
#WASM #LocalModels
One day, one feature: Make your tools in WASM
Write your own Mini Me tools as WebAssembly modules with TinyGo: sandboxed by wazero, with no secrets, no network and only the folders you open.
mini-me.org
October 28, 2026 at 6:25 AM
One day, one feature, day 7: write your Mini Me tools in WASM.
Compiled with @tinygo.org , run by #wazero in a #wasm sandbox: only the folders you open, no env vars (so no secrets), no network. A 4B model gets four tools, nothing else.
mini-me.org/p/20261028-m...
#WASM #LocalModels
Compiled with @tinygo.org , run by #wazero in a #wasm sandbox: only the folders you open, no env vars (so no secrets), no network. A 4B model gets four tools, nothing else.
mini-me.org/p/20261028-m...
#WASM #LocalModels
The study benchmarked five local LLMs on an ASUS Ascent GX10 server with 128 GB memory using the llm-compile-bench suite. Unlike token-per-second metrics, the method verifies if code compiles and tests pass across six programming languages over 30 total attempts.
#LLM #LocalModels #Compilation
#LLM #LocalModels #Compilation
gpt-oss-120b passed tests in 30 attempts
Source: HackerNews AI
realfeedapp.com
October 28, 2026 at 11:21 AM
The study benchmarked five local LLMs on an ASUS Ascent GX10 server with 128 GB memory using the llm-compile-bench suite. Unlike token-per-second metrics, the method verifies if code compiles and tests pass across six programming languages over 30 total attempts.
#LLM #LocalModels #Compilation
#LLM #LocalModels #Compilation
One day, one feature, day 6: Mini Me speaks MCP.
A few lines of YAML and a 4B local model (Qwen3.5) queries Wikipedia, then Context7 to explain how to connect to Redis in Rust from the official docs, not its training corpus.
mini-me.org/p/20261027-m...
#LocalModels #MCP
A few lines of YAML and a 4B local model (Qwen3.5) queries Wikipedia, then Context7 to explain how to connect to Redis in Rust from the official docs, not its training corpus.
mini-me.org/p/20261027-m...
#LocalModels #MCP
One day, one feature: Connect Mini Me to the world with MCP
Give a Mini Me agent MCP superpowers with a few lines of YAML: query Wikipedia, then add Context7 so a small local model can search up-to-date library docs.
mini-me.org
October 27, 2026 at 6:05 AM
One day, one feature, day 6: Mini Me speaks MCP.
A few lines of YAML and a 4B local model (Qwen3.5) queries Wikipedia, then Context7 to explain how to connect to Redis in Rust from the official docs, not its training corpus.
mini-me.org/p/20261027-m...
#LocalModels #MCP
A few lines of YAML and a 4B local model (Qwen3.5) queries Wikipedia, then Context7 to explain how to connect to Redis in Rust from the official docs, not its training corpus.
mini-me.org/p/20261027-m...
#LocalModels #MCP
One day, one feature, day 5: Mini Me v1.0.1 is out 🎉
With `unloadModels: true`, each agent's model is unloaded from memory before handing off to another one. Several agents, several small local models, and no more frozen laptop.
mini-me.org/p/20261026-m...
#LocalModels
With `unloadModels: true`, each agent's model is unloaded from memory before handing off to another one. Several agents, several small local models, and no more frozen laptop.
mini-me.org/p/20261026-m...
#LocalModels
One day, one feature: Automatically unloading models from memory
Mini Me v1.0.1 adds unloadModels: true, which unloads each agent's model between hand-offs so multi-agent setups with small local models don't exhaust your RAM.
mini-me.org
October 26, 2026 at 6:58 AM
One day, one feature, day 5: Mini Me v1.0.1 is out 🎉
With `unloadModels: true`, each agent's model is unloaded from memory before handing off to another one. Several agents, several small local models, and no more frozen laptop.
mini-me.org/p/20261026-m...
#LocalModels
With `unloadModels: true`, each agent's model is unloaded from memory before handing off to another one. Several agents, several small local models, and no more frozen laptop.
mini-me.org/p/20261026-m...
#LocalModels
One day, one feature, day 4: Mini Me's "long-term" memory 🧠
Turn on sessions and every conversation is saved. List them with /sessions, reload one with /resume, and let the model search its own past with search_memory.
mini-me.org/p/20261025-m...
#LocalModels
Turn on sessions and every conversation is saved. List them with /sessions, reload one with /resume, and let the model search its own past with search_memory.
mini-me.org/p/20261025-m...
#LocalModels
One day, one feature: Mini Me and its "long-term" memory
Turn on Mini Me sessions to save every conversation, list and resume past sessions, and let the model search its own memory with search_memory.
mini-me.org
October 25, 2026 at 6:06 AM
One day, one feature, day 4: Mini Me's "long-term" memory 🧠
Turn on sessions and every conversation is saved. List them with /sessions, reload one with /resume, and let the model search its own past with search_memory.
mini-me.org/p/20261025-m...
#LocalModels
Turn on sessions and every conversation is saved. List them with /sessions, reload one with /resume, and let the model search its own past with search_memory.
mini-me.org/p/20261025-m...
#LocalModels
One day, one feature, day 3: decision models 🧙
A small model fine-tuned to choose, not to write. With d1-3B, a Mini Me decider picks my D&D wizard's spell, with a probability for each; a Go hook passes it to the Dungeon Master.
mini-me.org/p/20261024-m...
#LocalModels
A small model fine-tuned to choose, not to write. With d1-3B, a Mini Me decider picks my D&D wizard's spell, with a probability for each; a Go hook passes it to the Dungeon Master.
mini-me.org/p/20261024-m...
#LocalModels
One day, one feature: Decision models & Wizardry
Use a small decision model with Mini Me: a decider agent that picks the best spell for a D&D wizard, with a probability for each option, in one pass.
mini-me.org
October 24, 2026 at 7:53 AM
One day, one feature, day 3: decision models 🧙
A small model fine-tuned to choose, not to write. With d1-3B, a Mini Me decider picks my D&D wizard's spell, with a probability for each; a Go hook passes it to the Dungeon Master.
mini-me.org/p/20261024-m...
#LocalModels
A small model fine-tuned to choose, not to write. With d1-3B, a Mini Me decider picks my D&D wizard's spell, with a probability for each; a Go hook passes it to the Dungeon Master.
mini-me.org/p/20261024-m...
#LocalModels
One day, one feature, day 2: tools 🧰
A model only produces text/data. Mini Me runs the tools: bash and the other built-in tools, plus the ones you declare in a few lines of YAML. An explicitly declared tool increases the model's detection success.
mini-me.org/p/20261023-m...
#LocalModels #sbx
A model only produces text/data. Mini Me runs the tools: bash and the other built-in tools, plus the ones you declare in a few lines of YAML. An explicitly declared tool increases the model's detection success.
mini-me.org/p/20261023-m...
#LocalModels #sbx
One day, one feature: Mini Me's built-in tools and declared tools
How Mini Me runs tools for a local model: the agent loop, the built-in tools led by bash, and how to declare your own tools in a few lines of YAML.
mini-me.org
October 23, 2026 at 4:50 AM
One day, one feature, day 2: tools 🧰
A model only produces text/data. Mini Me runs the tools: bash and the other built-in tools, plus the ones you declare in a few lines of YAML. An explicitly declared tool increases the model's detection success.
mini-me.org/p/20261023-m...
#LocalModels #sbx
A model only produces text/data. Mini Me runs the tools: bash and the other built-in tools, plus the ones you declare in a few lines of YAML. An explicitly declared tool increases the model's detection success.
mini-me.org/p/20261023-m...
#LocalModels #sbx
New series: "One day, one feature" 🗓️
Day 1: mm init, a wizard that writes your first Mini Me agent.yaml. Pick a provider, a model, its family, an agent profile and your machine size, and you get a base config tuned for that model.
mini-me.org/p/20261022-m...
#LocalModels #sbx
Day 1: mm init, a wizard that writes your first Mini Me agent.yaml. Pick a provider, a model, its family, an agent profile and your machine size, and you get a base config tuned for that model.
mini-me.org/p/20261022-m...
#LocalModels #sbx
One day, one feature: `mm init`
Meet mm init, the Mini Me setup wizard: pick a provider, a model, an agent profile and your machine size to get a ready-to-use agent.yaml in minutes.
mini-me.org
October 22, 2026 at 5:27 AM
New series: "One day, one feature" 🗓️
Day 1: mm init, a wizard that writes your first Mini Me agent.yaml. Pick a provider, a model, its family, an agent profile and your machine size, and you get a base config tuned for that model.
mini-me.org/p/20261022-m...
#LocalModels #sbx
Day 1: mm init, a wizard that writes your first Mini Me agent.yaml. Pick a provider, a model, its family, an agent profile and your machine size, and you get a base config tuned for that model.
mini-me.org/p/20261022-m...
#LocalModels #sbx
Added a guardrail model to Mini Me: IBM's Granite Guardian 3B scores prompts & responses for harm, bias, jailbreaks; fully local. Its system message isn't instructions, it's the risk name to check.
mini-me.org/p/20261020-g...
#LocalModels #Guardrails
mini-me.org/p/20261020-g...
#LocalModels #Guardrails
How to use a "guardrail" model with Mini Me
Use IBM's Granite Guardian 3B as a guardrail model with Mini Me, checking prompts and responses for harm, bias and jailbreak attempts.
mini-me.org
October 20, 2026 at 5:01 AM
Added a guardrail model to Mini Me: IBM's Granite Guardian 3B scores prompts & responses for harm, bias, jailbreaks; fully local. Its system message isn't instructions, it's the risk name to check.
mini-me.org/p/20261020-g...
#LocalModels #Guardrails
mini-me.org/p/20261020-g...
#LocalModels #Guardrails
Can I start learning Rust with a "not too big" local model? Today, no Claude Code: 80% with my 🧠, 20% with 🤖
Mini Me + Mellum2-12B-A2.5B as a teacher: first program, structs, mutability, methods.
mini-me.org/p/20261019-m...
#Rust #LocalModels
Mini Me + Mellum2-12B-A2.5B as a teacher: first program, structs, mutability, methods.
mini-me.org/p/20261019-m...
#Rust #LocalModels
Learning Rust gently with Mellum2-12B-A2.5B-Instruct and Mini Me (Part 1)
Learning Rust from scratch with a small local coding model: Mini Me and Mellum2-12B-A2.5B as a teacher for a first program, structs, mutability and methods.
mini-me.org
October 19, 2026 at 5:45 AM
Can I start learning Rust with a "not too big" local model? Today, no Claude Code: 80% with my 🧠, 20% with 🤖
Mini Me + Mellum2-12B-A2.5B as a teacher: first program, structs, mutability, methods.
mini-me.org/p/20261019-m...
#Rust #LocalModels
Mini Me + Mellum2-12B-A2.5B as a teacher: first program, structs, mutability, methods.
mini-me.org/p/20261019-m...
#Rust #LocalModels
Can I start learning Rust with a "not too big" local model? Today, no Claude Code: 80% with my 🧠, 20% with 🤖
Mini Me + Mellum2-12B-A2.5B as a teacher: first program, structs, mutability, methods.
#Rust #LocalModels
Mini Me + Mellum2-12B-A2.5B as a teacher: first program, structs, mutability, methods.
#Rust #LocalModels
October 19, 2026 at 9:51 AM
Can I start learning Rust with a "not too big" local model? Today, no Claude Code: 80% with my 🧠, 20% with 🤖
Mini Me + Mellum2-12B-A2.5B as a teacher: first program, structs, mutability, methods.
#Rust #LocalModels
Mini Me + Mellum2-12B-A2.5B as a teacher: first program, structs, mutability, methods.
#Rust #LocalModels
I don't always use VS Code: when I need to stay focused, I use Zed. And Zed can connect to a @docker.com sbx sandbox over SSH 🎉
One sbxenv.yaml, one sbx env create, and Zed opens in a secure Linux sandbox with Mini Me, Nushell and Rust.
mini-me.org/p/20261018-s...
#sbx #LocalModels
One sbxenv.yaml, one sbx env create, and Zed opens in a secure Linux sandbox with Mini Me, Nushell and Rust.
mini-me.org/p/20261018-s...
#sbx #LocalModels
Using Mini Me in a secure and comfortable development environment
Run Mini Me in a secure sbx sandbox and code in it from Zed over SSH, with new workload and mixin kits declared in a single sbxenv.yaml file.
mini-me.org
October 18, 2026 at 6:57 AM
I don't always use VS Code: when I need to stay focused, I use Zed. And Zed can connect to a @docker.com sbx sandbox over SSH 🎉
One sbxenv.yaml, one sbx env create, and Zed opens in a secure Linux sandbox with Mini Me, Nushell and Rust.
mini-me.org/p/20261018-s...
#sbx #LocalModels
One sbxenv.yaml, one sbx env create, and Zed opens in a secure Linux sandbox with Mini Me, Nushell and Rust.
mini-me.org/p/20261018-s...
#sbx #LocalModels
Mini Me agents can talk to each other over #ACP. So I built a team: a coordinator (Qwen3.5 0.8B) that hands my Go and Rust questions to two specialists sharing the same Mellum2 model. Interactive docs, all local 🤗
mini-me.org/p/20261015-m...
#LocalModels #golang #rustlang
mini-me.org/p/20261015-m...
#LocalModels #golang #rustlang
Building a team of Mini Mes with ACP
Build a team of local Mini Me agents talking over ACP: a coordinator that routes your Go and Rust questions to two documentation specialists.
mini-me.org
October 15, 2026 at 6:08 PM
Mini Me agents can talk to each other over #ACP. So I built a team: a coordinator (Qwen3.5 0.8B) that hands my Go and Rust questions to two specialists sharing the same Mellum2 model. Interactive docs, all local 🤗
mini-me.org/p/20261015-m...
#LocalModels #golang #rustlang
mini-me.org/p/20261015-m...
#LocalModels #golang #rustlang
Structured output with Mini Me: you describe the JSON you want with Go structs (yes, I love Go 😉), and a tiny local model (Gemma 4 E2B) returns exactly that. Example: a pizzaiolo agent listing a pizza's ingredients 🍕
mini-me.org/p/20261016-s...
#LocalModels #golang
mini-me.org/p/20261016-s...
#LocalModels #golang
Doing JSON structured output with Mini Me
Get JSON answers that follow a schema from a local model with Mini Me, using Go struct notation, then use them from a coordinator agent in the TUI.
mini-me.org
October 16, 2026 at 5:36 AM
Structured output with Mini Me: you describe the JSON you want with Go structs (yes, I love Go 😉), and a tiny local model (Gemma 4 E2B) returns exactly that. Example: a pizzaiolo agent listing a pizza's ingredients 🍕
mini-me.org/p/20261016-s...
#LocalModels #golang
mini-me.org/p/20261016-s...
#LocalModels #golang
New #sbx kit: Mini Me Editor. It bundles the Mini Me agent and the #Eclipse #Theia web IDE in a single @docker.com sandbox, so I get a fully isolated dev environment in my browser. A bit like GitPod 🍊, but on my machine 🤗
mini-me.org/p/20261013-m...
#sbx #LocalModels
mini-me.org/p/20261013-m...
#sbx #LocalModels
Mini Me Editor: an `sbx` kit that bundles Mini Me and Eclipse Theia
Mini Me Editor is an sbx kit bundling the Mini Me agent with the Eclipse Theia web IDE, for a fully sandboxed dev environment in your browser.
mini-me.org
October 13, 2026 at 4:55 PM
New #sbx kit: Mini Me Editor. It bundles the Mini Me agent and the #Eclipse #Theia web IDE in a single @docker.com sandbox, so I get a fully isolated dev environment in my browser. A bit like GitPod 🍊, but on my machine 🤗
mini-me.org/p/20261013-m...
#sbx #LocalModels
mini-me.org/p/20261013-m...
#sbx #LocalModels
#ACP is to coding agents what #LSP is to language servers: one protocol, any compatible editor.
Mini Me speaks it 🙂 Here is how to use it from #Zed and #VSCode (with ACP Patchbay), directly or from inside a @docker.com sbx sandbox.
mini-me.org/p/20261011-m...
#LocalModels
Mini Me speaks it 🙂 Here is how to use it from #Zed and #VSCode (with ACP Patchbay), directly or from inside a @docker.com sbx sandbox.
mini-me.org/p/20261011-m...
#LocalModels
Mini Me and the ACP protocol (Agent Client Protocol)
Plug Mini Me into Zed and VSCode through the Agent Client Protocol, directly or running inside a Docker sbx sandbox, with a ready-made translator agent.
mini-me.org
October 11, 2026 at 8:51 AM
#ACP is to coding agents what #LSP is to language servers: one protocol, any compatible editor.
Mini Me speaks it 🙂 Here is how to use it from #Zed and #VSCode (with ACP Patchbay), directly or from inside a @docker.com sbx sandbox.
mini-me.org/p/20261011-m...
#LocalModels
Mini Me speaks it 🙂 Here is how to use it from #Zed and #VSCode (with ACP Patchbay), directly or from inside a @docker.com sbx sandbox.
mini-me.org/p/20261011-m...
#LocalModels
@devoxx.com Belgium reboosts your brain, so my baby Mini Me got a few new features during these 5 days 🙂
v0.3.0: approve tool calls or not (yolo: false), agents calling other agents, request traces, JSON answers, AGENTS.md...
mini-me.org/p/20261010-m...
#LocalModels
v0.3.0: approve tool calls or not (yolo: false), agents calling other agents, request traces, JSON answers, AGENTS.md...
mini-me.org/p/20261010-m...
#LocalModels
Mini Me release v0.3.0
What is new in Mini Me v0.3.0, the Devoxx Belgium release: approval mode, agents calling agents, request traces, JSON answers, AGENTS.md and an sbx kit.
mini-me.org
October 10, 2026 at 8:32 AM
@devoxx.com Belgium reboosts your brain, so my baby Mini Me got a few new features during these 5 days 🙂
v0.3.0: approve tool calls or not (yolo: false), agents calling other agents, request traces, JSON answers, AGENTS.md...
mini-me.org/p/20261010-m...
#LocalModels
v0.3.0: approve tool calls or not (yolo: false), agents calling other agents, request traces, JSON answers, AGENTS.md...
mini-me.org/p/20261010-m...
#LocalModels
Running an AI agent directly on your machine? It sees your configs, ssh keys, env variables, secrets...
So Mini Me now has its @docker.com sbx kit: two files and one command to run it in a sandbox. You'll see, it's quick.
mini-me.org/p/20261010-m...
#sbx #LocalModels
So Mini Me now has its @docker.com sbx kit: two files and one command to run it in a sandbox. You'll see, it's quick.
mini-me.org/p/20261010-m...
#sbx #LocalModels
Don't let your agents roam free in the wild: Mini Me gets its `sbx` kit
Build a Docker sbx kit for Mini Me to run the agent in an isolated sandbox, locally or from a remote repository, and extend it with additional kits.
mini-me.org
October 10, 2026 at 9:44 AM
Running an AI agent directly on your machine? It sees your configs, ssh keys, env variables, secrets...
So Mini Me now has its @docker.com sbx kit: two files and one command to run it in a sandbox. You'll see, it's quick.
mini-me.org/p/20261010-m...
#sbx #LocalModels
So Mini Me now has its @docker.com sbx kit: two files and one command to run it in a sandbox. You'll see, it's quick.
mini-me.org/p/20261010-m...
#sbx #LocalModels
I hope a nice, quantitized version of this shows up so I can try it with #mlx #omlx.
#ai #localmodels #datasovereignty https://flipboard.com/@cnet/tech-tips-%F0%9F%93%B1%F0%9F%92%BB%F0%9F%93%A1-a20abmejz/-/a-R7H13fpdRD2YWFm63mDbgg%3Aa%3A24934323-%2F0
#ai #localmodels #datasovereignty https://flipboard.com/@cnet/tech-tips-%F0%9F%93%B1%F0%9F%92%BB%F0%9F%93%A1-a20abmejz/-/a-R7H13fpdRD2YWFm63mDbgg%3Aa%3A24934323-%2F0
October 8, 2026 at 9:47 PM
I hope a nice, quantitized version of this shows up so I can try it with #mlx #omlx.
#ai #localmodels #datasovereignty https://flipboard.com/@cnet/tech-tips-%F0%9F%93%B1%F0%9F%92%BB%F0%9F%93%A1-a20abmejz/-/a-R7H13fpdRD2YWFm63mDbgg%3Aa%3A24934323-%2F0
#ai #localmodels #datasovereignty https://flipboard.com/@cnet/tech-tips-%F0%9F%93%B1%F0%9F%92%BB%F0%9F%93%A1-a20abmejz/-/a-R7H13fpdRD2YWFm63mDbgg%3Aa%3A24934323-%2F0