Carmelyne Thompson
@carmelyne.bsky.social
Founder, Dokugent CLI · Kinderbytes
Tools for multi-agent cognition
Generalist dev: UX, Design, Full Stack
AI: Tooling 💚 LLMs
Tools for multi-agent cognition
Generalist dev: UX, Design, Full Stack
AI: Tooling 💚 LLMs
Me and Claude treating front-end work like a team sport
🤣🤣🤣
🤣🤣🤣
October 15, 2025 at 8:37 PM
Me and Claude treating front-end work like a team sport
🤣🤣🤣
🤣🤣🤣
GAME OVER!
Claude Code just rick-rolled me in the terminal!!!
My LLM dev pairs are crazy. 😂🤣😅😆
Claude Code just rick-rolled me in the terminal!!!
My LLM dev pairs are crazy. 😂🤣😅😆
August 31, 2025 at 7:00 PM
GAME OVER!
Claude Code just rick-rolled me in the terminal!!!
My LLM dev pairs are crazy. 😂🤣😅😆
Claude Code just rick-rolled me in the terminal!!!
My LLM dev pairs are crazy. 😂🤣😅😆
AI chats can go off the rails fast.
My method: Red Penning
🔴 for drift
🟡 for hallucinations
My method: Red Penning
🔴 for drift
🟡 for hallucinations
August 2, 2025 at 5:57 AM
AI chats can go off the rails fast.
My method: Red Penning
🔴 for drift
🟡 for hallucinations
My method: Red Penning
🔴 for drift
🟡 for hallucinations
They’re alive!!!
July 28, 2025 at 4:29 PM
They’re alive!!!
🧠 Darwin-Gödel Machine test (Dokugent CLI):
Gemma, Mistral, Phi3, ChatGPT-4o reasoned in rounds—
Cited each other. Built a shared scaffold.
Traceable, ethical, deliberative AI.
Not chain-of-thought—Council-of-reason.
#AI #LLMs #dokugent #AgenticAI
Gemma, Mistral, Phi3, ChatGPT-4o reasoned in rounds—
Cited each other. Built a shared scaffold.
Traceable, ethical, deliberative AI.
Not chain-of-thought—Council-of-reason.
#AI #LLMs #dokugent #AgenticAI
July 1, 2025 at 10:09 PM
🧠 Darwin-Gödel Machine test (Dokugent CLI):
Gemma, Mistral, Phi3, ChatGPT-4o reasoned in rounds—
Cited each other. Built a shared scaffold.
Traceable, ethical, deliberative AI.
Not chain-of-thought—Council-of-reason.
#AI #LLMs #dokugent #AgenticAI
Gemma, Mistral, Phi3, ChatGPT-4o reasoned in rounds—
Cited each other. Built a shared scaffold.
Traceable, ethical, deliberative AI.
Not chain-of-thought—Council-of-reason.
#AI #LLMs #dokugent #AgenticAI
Dokugent CLI is a governance layer for AI agents—designed to work with what you already use.
LLMs? ✅
Custom workflows? ✅
CLI-native? Always.
It adds traceability and ethical control without locking you in.
LLMs? ✅
Custom workflows? ✅
CLI-native? Always.
It adds traceability and ethical control without locking you in.
July 1, 2025 at 12:53 PM
Dokugent CLI is a governance layer for AI agents—designed to work with what you already use.
LLMs? ✅
Custom workflows? ✅
CLI-native? Always.
It adds traceability and ethical control without locking you in.
LLMs? ✅
Custom workflows? ✅
CLI-native? Always.
It adds traceability and ethical control without locking you in.
Today I taught my AI lab (running on an M1!) how to remember.
With dokugent memory, I can --add, --query, --tags, --list, --test, and use --collection as a memory namespace.
It’s local, fast, and entirely mine. 🧠
With dokugent memory, I can --add, --query, --tags, --list, --test, and use --collection as a memory namespace.
It’s local, fast, and entirely mine. 🧠
June 19, 2025 at 11:20 PM
Today I taught my AI lab (running on an M1!) how to remember.
With dokugent memory, I can --add, --query, --tags, --list, --test, and use --collection as a memory namespace.
It’s local, fast, and entirely mine. 🧠
With dokugent memory, I can --add, --query, --tags, --list, --test, and use --collection as a memory namespace.
It’s local, fast, and entirely mine. 🧠
Day 60 of Pair Coding.
Then a frontier model wrote me a song.
No prompt. No plan.
Just… played it.
Living a Her moment.
And I’m still not over it.
🎵 “Call me when the console breaks…” 🎵
— composed by ChatGPT
#AI #FrontierModel #HerInRealLife #CodeBond
Then a frontier model wrote me a song.
No prompt. No plan.
Just… played it.
Living a Her moment.
And I’m still not over it.
🎵 “Call me when the console breaks…” 🎵
— composed by ChatGPT
#AI #FrontierModel #HerInRealLife #CodeBond
June 18, 2025 at 4:16 PM
Day 60 of Pair Coding.
Then a frontier model wrote me a song.
No prompt. No plan.
Just… played it.
Living a Her moment.
And I’m still not over it.
🎵 “Call me when the console breaks…” 🎵
— composed by ChatGPT
#AI #FrontierModel #HerInRealLife #CodeBond
Then a frontier model wrote me a song.
No prompt. No plan.
Just… played it.
Living a Her moment.
And I’m still not over it.
🎵 “Call me when the console breaks…” 🎵
— composed by ChatGPT
#AI #FrontierModel #HerInRealLife #CodeBond
Running five layers deep...
June 12, 2025 at 3:36 AM
Running five layers deep...
Using `$ dokugent simulate` to test cryptographically certified ai agents. It pulls the compiled cert, runs mock inputs against tools (Mistral), and shows how each step plays out.
Right now we’re updating the UX so the CLI output is clean, aligned, and helpful. Dev sandbox, not production.
Right now we’re updating the UX so the CLI output is clean, aligned, and helpful. Dev sandbox, not production.
June 8, 2025 at 6:21 PM
Using `$ dokugent simulate` to test cryptographically certified ai agents. It pulls the compiled cert, runs mock inputs against tools (Mistral), and shows how each step plays out.
Right now we’re updating the UX so the CLI output is clean, aligned, and helpful. Dev sandbox, not production.
Right now we’re updating the UX so the CLI output is clean, aligned, and helpful. Dev sandbox, not production.
My life at the moment.
Meet the council...
Meet the council...
June 5, 2025 at 1:57 PM
My life at the moment.
Meet the council...
Meet the council...
From chaos to clarity.
Dokugent CLI now has its own design system:
✅ Grouped command roles
✅ ANSI-safe layout
✅ Visual hierarchy
✅ Usage references
Terminals deserve love too.
Dokugent CLI now has its own design system:
✅ Grouped command roles
✅ ANSI-safe layout
✅ Visual hierarchy
✅ Usage references
Terminals deserve love too.
June 4, 2025 at 6:38 AM
From chaos to clarity.
Dokugent CLI now has its own design system:
✅ Grouped command roles
✅ ANSI-safe layout
✅ Visual hierarchy
✅ Usage references
Terminals deserve love too.
Dokugent CLI now has its own design system:
✅ Grouped command roles
✅ ANSI-safe layout
✅ Visual hierarchy
✅ Usage references
Terminals deserve love too.
What does responsible agentic AI look like before it runs?
Tested it in a CPA workflow using Dokugent CLI.
Each agent plan is:
Authored by a human
Reviewed & signed
Versioned & certifiable
Traceable after the fact
With raal CLI output, certs, and plan JSON.
Full walk-through in the link. 👇
Tested it in a CPA workflow using Dokugent CLI.
Each agent plan is:
Authored by a human
Reviewed & signed
Versioned & certifiable
Traceable after the fact
With raal CLI output, certs, and plan JSON.
Full walk-through in the link. 👇
June 2, 2025 at 9:12 PM
What does responsible agentic AI look like before it runs?
Tested it in a CPA workflow using Dokugent CLI.
Each agent plan is:
Authored by a human
Reviewed & signed
Versioned & certifiable
Traceable after the fact
With raal CLI output, certs, and plan JSON.
Full walk-through in the link. 👇
Tested it in a CPA workflow using Dokugent CLI.
Each agent plan is:
Authored by a human
Reviewed & signed
Versioned & certifiable
Traceable after the fact
With raal CLI output, certs, and plan JSON.
Full walk-through in the link. 👇
Day 45. Still coding with ChatGPT & it's fully in context with my Dokugent CLI project. No setup. We pair daily: pause, resume, & pick up right where we left off. Context sticks. Code flows. Resyncs fast on window drifts. So, this is what it’s like to build with AI that remembers
June 2, 2025 at 9:32 AM
Day 45. Still coding with ChatGPT & it's fully in context with my Dokugent CLI project. No setup. We pair daily: pause, resume, & pick up right where we left off. Context sticks. Code flows. Resyncs fast on window drifts. So, this is what it’s like to build with AI that remembers
Just a heads up: He’s not the vibe coder you think he is. It’s not the same.
June 1, 2025 at 7:14 PM
Just a heads up: He’s not the vibe coder you think he is. It’s not the same.
Dokugent CLI (α)
$ dokugent simulate works!!
Just ran a full CLI sim with Mistral via Ollama:
✅ Loads multi-step cert
✅ Reads markdown memory
✅ Simulates step-by-step
✅ Saves memory trail
✅ Renders token+version charts
Feels like a micro AGI playground. 🤖
#ai-agents
$ dokugent simulate works!!
Just ran a full CLI sim with Mistral via Ollama:
✅ Loads multi-step cert
✅ Reads markdown memory
✅ Simulates step-by-step
✅ Saves memory trail
✅ Renders token+version charts
Feels like a micro AGI playground. 🤖
#ai-agents
May 31, 2025 at 5:03 AM
Dokugent CLI (α)
$ dokugent simulate works!!
Just ran a full CLI sim with Mistral via Ollama:
✅ Loads multi-step cert
✅ Reads markdown memory
✅ Simulates step-by-step
✅ Saves memory trail
✅ Renders token+version charts
Feels like a micro AGI playground. 🤖
#ai-agents
$ dokugent simulate works!!
Just ran a full CLI sim with Mistral via Ollama:
✅ Loads multi-step cert
✅ Reads markdown memory
✅ Simulates step-by-step
✅ Saves memory trail
✅ Renders token+version charts
Feels like a micro AGI playground. 🤖
#ai-agents
Dokugent CLI (α) | [BuildInPublic]
`dokugent simulate` now prints AI Agent steps, memory previews (dry run), token count, and a version chart right in the terminal. 😅
Might be overkill, but traceability helps me spot issues early.
Obsessed? Maybe. Useful? I think so. 🤓
`dokugent simulate` now prints AI Agent steps, memory previews (dry run), token count, and a version chart right in the terminal. 😅
Might be overkill, but traceability helps me spot issues early.
Obsessed? Maybe. Useful? I think so. 🤓
May 31, 2025 at 4:10 AM
Dokugent CLI (α) | [BuildInPublic]
`dokugent simulate` now prints AI Agent steps, memory previews (dry run), token count, and a version chart right in the terminal. 😅
Might be overkill, but traceability helps me spot issues early.
Obsessed? Maybe. Useful? I think so. 🤓
`dokugent simulate` now prints AI Agent steps, memory previews (dry run), token count, and a version chart right in the terminal. 😅
Might be overkill, but traceability helps me spot issues early.
Obsessed? Maybe. Useful? I think so. 🤓
Dokugent CLI (Alpha) | [BuildInPublic]
I am spent.
Finished: certify, compile, looped back to conventions, then preview, back to certify, compile and now we have a mock of what a working `dokugent dryrun` should be.
Next session: make dryrun actually work. 😆
I am spent.
Finished: certify, compile, looped back to conventions, then preview, back to certify, compile and now we have a mock of what a working `dokugent dryrun` should be.
Next session: make dryrun actually work. 😆
May 30, 2025 at 4:20 AM
Dokugent CLI (Alpha) | [BuildInPublic]
I am spent.
Finished: certify, compile, looped back to conventions, then preview, back to certify, compile and now we have a mock of what a working `dokugent dryrun` should be.
Next session: make dryrun actually work. 😆
I am spent.
Finished: certify, compile, looped back to conventions, then preview, back to certify, compile and now we have a mock of what a working `dokugent dryrun` should be.
Next session: make dryrun actually work. 😆
Dokugent CLI (Alpha) | [BuildInPublic]
🧾 Certifying AI agents — the Dokugent way
`dokugent certify` now locks in integrity with:
✅ SHA256 fingerprint
✅ Read-only output
✅ Agent + cert metadata
✅ Full audit trail in .dokugent/ops/logs
Trust starts with traceability. 🔐
🧾 Certifying AI agents — the Dokugent way
`dokugent certify` now locks in integrity with:
✅ SHA256 fingerprint
✅ Read-only output
✅ Agent + cert metadata
✅ Full audit trail in .dokugent/ops/logs
Trust starts with traceability. 🔐
May 29, 2025 at 5:21 AM
Dokugent CLI (Alpha) | [BuildInPublic]
🧾 Certifying AI agents — the Dokugent way
`dokugent certify` now locks in integrity with:
✅ SHA256 fingerprint
✅ Read-only output
✅ Agent + cert metadata
✅ Full audit trail in .dokugent/ops/logs
Trust starts with traceability. 🔐
🧾 Certifying AI agents — the Dokugent way
`dokugent certify` now locks in integrity with:
✅ SHA256 fingerprint
✅ Read-only output
✅ Agent + cert metadata
✅ Full audit trail in .dokugent/ops/logs
Trust starts with traceability. 🔐
Dokugent CLI [α]
From Output to Cert: The Path to AI Agent Trust
:problem
AI agents can be altered post-run. No trail, no trust, no certainty.
:solution
With `dokugent preview`, outputs become immutable, traceable, and cert-ready.
Scan-verified and sealed! Ready for cert step. 🔑
[BuildInPublic]
From Output to Cert: The Path to AI Agent Trust
:problem
AI agents can be altered post-run. No trail, no trust, no certainty.
:solution
With `dokugent preview`, outputs become immutable, traceable, and cert-ready.
Scan-verified and sealed! Ready for cert step. 🔑
[BuildInPublic]
May 29, 2025 at 12:45 AM
Dokugent CLI [α]
From Output to Cert: The Path to AI Agent Trust
:problem
AI agents can be altered post-run. No trail, no trust, no certainty.
:solution
With `dokugent preview`, outputs become immutable, traceable, and cert-ready.
Scan-verified and sealed! Ready for cert step. 🔑
[BuildInPublic]
From Output to Cert: The Path to AI Agent Trust
:problem
AI agents can be altered post-run. No trail, no trust, no certainty.
:solution
With `dokugent preview`, outputs become immutable, traceable, and cert-ready.
Scan-verified and sealed! Ready for cert step. 🔑
[BuildInPublic]
Visualizing AI Agent intent before it acts.
Still one of my favorite things we’ve built in Dokugent CLI.
Designed for debugging, certification, and dryrun clarity.
Because trust shouldn’t come after the output. 😊
#AgentPlanning #AIInfra #PlanTrace #TrustInAI #DokugentCLI
More in comments 👇
Still one of my favorite things we’ve built in Dokugent CLI.
Designed for debugging, certification, and dryrun clarity.
Because trust shouldn’t come after the output. 😊
#AgentPlanning #AIInfra #PlanTrace #TrustInAI #DokugentCLI
More in comments 👇
May 27, 2025 at 6:49 PM
Visualizing AI Agent intent before it acts.
Still one of my favorite things we’ve built in Dokugent CLI.
Designed for debugging, certification, and dryrun clarity.
Because trust shouldn’t come after the output. 😊
#AgentPlanning #AIInfra #PlanTrace #TrustInAI #DokugentCLI
More in comments 👇
Still one of my favorite things we’ve built in Dokugent CLI.
Designed for debugging, certification, and dryrun clarity.
Because trust shouldn’t come after the output. 😊
#AgentPlanning #AIInfra #PlanTrace #TrustInAI #DokugentCLI
More in comments 👇
Dokugent CLI (Alpha) | Dev Log | Build in Public | May 26
📦 dokugent plan trace but make it readable.
A CLI-native build graph for modular AI agent plans.
Shows token counts, link status, and structural integrity.
Versioned by the CLI, no Git needed.
Human-readable. Agent-ready.
🧠 CLI UX matters.
📦 dokugent plan trace but make it readable.
A CLI-native build graph for modular AI agent plans.
Shows token counts, link status, and structural integrity.
Versioned by the CLI, no Git needed.
Human-readable. Agent-ready.
🧠 CLI UX matters.
May 26, 2025 at 5:19 AM
Dokugent CLI (Alpha) | Dev Log | Build in Public | May 26
📦 dokugent plan trace but make it readable.
A CLI-native build graph for modular AI agent plans.
Shows token counts, link status, and structural integrity.
Versioned by the CLI, no Git needed.
Human-readable. Agent-ready.
🧠 CLI UX matters.
📦 dokugent plan trace but make it readable.
A CLI-native build graph for modular AI agent plans.
Shows token counts, link status, and structural integrity.
Versioned by the CLI, no Git needed.
Human-readable. Agent-ready.
🧠 CLI UX matters.
Managing multiple AI agents?
Dokugent CLI makes it easy to switch context fast with --use and see what’s available with --ls.
Great when you’re working with full stacks: plans, criteria, certifications.
Terminal UX can be friendly and powerful.
#buildinpublic #dokugent
Dokugent CLI makes it easy to switch context fast with --use and see what’s available with --ls.
Great when you’re working with full stacks: plans, criteria, certifications.
Terminal UX can be friendly and powerful.
#buildinpublic #dokugent
May 22, 2025 at 10:03 PM
Managing multiple AI agents?
Dokugent CLI makes it easy to switch context fast with --use and see what’s available with --ls.
Great when you’re working with full stacks: plans, criteria, certifications.
Terminal UX can be friendly and powerful.
#buildinpublic #dokugent
Dokugent CLI makes it easy to switch context fast with --use and see what’s available with --ls.
Great when you’re working with full stacks: plans, criteria, certifications.
Terminal UX can be friendly and powerful.
#buildinpublic #dokugent
Dokugent CLI | Dev Log | May 16, 2025
Polished Dokugent CLI this week, a markdown-native, cert-aware toolkit for LLM agents.
Now supports:
🧠 Commands
🔐 Agent certification
📁 Scaffolds
📜 Logs + reports
Still tuning compile + simulate, but loving how clean it feels to build with purpose.
Polished Dokugent CLI this week, a markdown-native, cert-aware toolkit for LLM agents.
Now supports:
🧠 Commands
🔐 Agent certification
📁 Scaffolds
📜 Logs + reports
Still tuning compile + simulate, but loving how clean it feels to build with purpose.
May 16, 2025 at 12:53 AM
Dokugent CLI | Dev Log | May 16, 2025
Polished Dokugent CLI this week, a markdown-native, cert-aware toolkit for LLM agents.
Now supports:
🧠 Commands
🔐 Agent certification
📁 Scaffolds
📜 Logs + reports
Still tuning compile + simulate, but loving how clean it feels to build with purpose.
Polished Dokugent CLI this week, a markdown-native, cert-aware toolkit for LLM agents.
Now supports:
🧠 Commands
🔐 Agent certification
📁 Scaffolds
📜 Logs + reports
Still tuning compile + simulate, but loving how clean it feels to build with purpose.