正在加载视频...

视频加载失败

返回首页

GPT-6 Astra + Business wiki + Meetings + YouTube videos + Claude memory + Codex memory + Projects + Skills + Agents = Fun

nateherk's profile picture

Nate Herk

31,710 subscribers

52,833 次观看 • 11 天前 •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

9 条评论

Ken 的头像
Ken10 天前

Does @nateherk even sleep? This guy is a machine. Great article though. Definitely going to build this.

Webster | JARVIS 的头像
Webster | JARVIS11 天前

haha this is basically my dream setup tbh codex memory alone would fix so much of my day

morgan huang 的头像
morgan huang11 天前

the stack isn't the hard part anymore. wiring nine tools together takes an afternoon now. the hard part is that a second brain inherits your first brain's blind spots. it recalls everything you wrote down and nothing you never decided. more memory, same judgment.

athrv.sh 的头像
athrv.sh10 天前

works until two of those memories disagree about the same fact

PeritumAI 的头像
PeritumAI10 天前

Stacking memory across tools only helps if each agent still has one job. Otherwise you get a second brain that argues with itself.

ThisMightWork 的头像
ThisMightWork11 天前

How are you keeping old meeting notes from overruling newer decisions? That’s the bit I’d want nailed down.

Veronn AI Marketing 的头像
Veronn AI Marketing9 天前

where do i watch the full video?

PeritumAI 的头像
PeritumAI11 天前

Fun stack. We still pin publish, pay, and send to a human before any of those tools get write access.

NASMA ELLIS 的头像
NASMA ELLIS11 天前

Looking 👀👀 to work together

相关视频

Claude Opus 5 vs GPT-6 Astra
0:40

Claude Opus 5 vs GPT-6 Astra

0xMarioNawfal

54,948 次观看 • 11 天前

This is an amazing Codex tip. Works even better when paired with persistent Codex memory files in Obsidian. Gave me 8 recommended skills relevant to active projects. Do try this!
0:34

This is an amazing Codex tip. Works even better when paired with persistent Codex memory files in Obsidian. Gave me 8 recommended skills relevant to active projects. Do try this!

Dan McAteer

253,402 次观看 • 3 个月前

You can switch from Claude Code to Codex with GPT-6 Astra without losing your setup, instructions or context by importing directly from Claude Code settings in three steps.
0:23

You can switch from Claude Code to Codex with GPT-6 Astra without losing your setup, instructions or context by importing directly from Claude Code settings in three steps.

0xMarioNawfal

38,902 次观看 • 10 天前

No game studio. No team. Solo developed. @HermesWorldAI With Claude + GPT and Hermes/ OpenClaw Agents. You can build anything right now. Focus on your harness. Your agentic skills, memory, orchestration loops. You can just build shit.
0:36

No game studio. No team. Solo developed. @HermesWorldAI With Claude + GPT and Hermes/ OpenClaw Agents. You can build anything right now. Focus on your harness. Your agentic skills, memory, orchestration loops. You can just build shit.

Eric ⚡️ Building...

57,415 次观看 • 2 个月前

Introducing supermemory for Codex! give your codex better memory while having it interoperable between every other provider - OpenCode, Claude code, etc 1. Codex can see the timeline 2. It has your profile 3. Both explicit and implicit (dreaming) memory
1:44

Introducing supermemory for Codex! give your codex better memory while having it interoperable between every other provider - OpenCode, Claude code, etc 1. Codex can see the timeline 2. It has your profile 3. Both explicit and implicit (dreaming) memory

Dhravya Shah

29,816 次观看 • 4 个月前

Memory Store (Memory Store) gives your team and AI agents a shared company brain. Your team's knowledge & decisions are scattered across slack, emails, and people's heads. Memory Store turns them into a living wiki for your agents and teammates. Congrats on the launch, Ishita Jindal & Diwank Singh Tomer!
1:09

Memory Store (Memory Store) gives your team and AI agents a shared company brain. Your team's knowledge & decisions are scattered across slack, emails, and people's heads. Memory Store turns them into a living wiki for your agents and teammates. Congrats on the launch, Ishita Jindal & Diwank Singh Tomer!

Y Combinator

246,476 次观看 • 4 个月前

Starting today, agents can use Mastra Studio, not just humans We shipped CLI Actions so your Claude Code, Codex, or Cursor agent can run Mastra agents/workflows, search memory, query traces, and turn failures into datasets:
0:30

Starting today, agents can use Mastra Studio, not just humans We shipped CLI Actions so your Claude Code, Codex, or Cursor agent can run Mastra agents/workflows, search memory, query traces, and turn failures into datasets:

Sam Bhagwat

12,806 次观看 • 2 个月前

AI has terrible memory Introducing Micro, an agent that remembers more than Claude, Codex & OpenClaw Leave a comment (eg "memory") & I'll send 30 days for free to try it
2:29

AI has terrible memory Introducing Micro, an agent that remembers more than Claude, Codex & OpenClaw Leave a comment (eg "memory") & I'll send 30 days for free to try it

brett goldstein

886,076 次观看 • 3 个月前

Built a 3-layer Memory Stack that wires Claude Code directly into Obsidian with skills so it never forgets your project DNA, your notes, your standards, or your goals. Fixes most of Claude Code's memory issues.
1:38

Built a 3-layer Memory Stack that wires Claude Code directly into Obsidian with skills so it never forgets your project DNA, your notes, your standards, or your goals. Fixes most of Claude Code's memory issues.

WorldofAI

115,934 次观看 • 5 个月前

Since no GPT-6-Astra, Here's the Claude Fable 5.1 Subway FPS ported to Apple Vision Pro
1:42

Since no GPT-6-Astra, Here's the Claude Fable 5.1 Subway FPS ported to Apple Vision Pro

BijanBowen

19,219 次观看 • 14 天前

I've spent 2 months teaching my AI how I work again and again Claude Code knows one thing. Cursor knows another. Codex starts from scratch. OpenClaw has its own memory. None of them remember what the others learned. Memmy brings those histories into one local, user-controlled memory—so you can switch agents without re-explaining your projects, decisions, and preferences. Switch agents without rebuilding your context. Let every AI remember the same you. GitHub: ProductHunt:
1:13

I've spent 2 months teaching my AI how I work again and again Claude Code knows one thing. Cursor knows another. Codex starts from scratch. OpenClaw has its own memory. None of them remember what the others learned. Memmy brings those histories into one local, user-controlled memory—so you can switch agents without re-explaining your projects, decisions, and preferences. Switch agents without rebuilding your context. Let every AI remember the same you. GitHub: ProductHunt:

Priyank Ahuja

13,228 次观看 • 1 个月前

Introducing OpenKnowledge, the best markdown IDE for humans and agents. Open source. Local and private. LLM-wiki ready. Use with Claude, Codex, and your favorite agent today.
0:39

Introducing OpenKnowledge, the best markdown IDE for humans and agents. Open source. Local and private. LLM-wiki ready. Use with Claude, Codex, and your favorite agent today.

Nick Gomez

325,946 次观看 • 2 个月前

Here's exactly how I edit videos using GPT-6 Astra + DaVinci MCP
9:09

Here's exactly how I edit videos using GPT-6 Astra + DaVinci MCP

Alex

33,355 次观看 • 6 天前

My balance went down as I was recording a YouTube video (at 0:01), I have no idea what's going on anymore with the budget limits. Using GPT-6 Astra in Codex.
0:33

My balance went down as I was recording a YouTube video (at 0:01), I have no idea what's going on anymore with the budget limits. Using GPT-6 Astra in Codex.

Wesley

19,107 次观看 • 8 天前

Our best model yet: GPT-6 Astra. – Build agents for complex long-running work. – Solve engineering problems with less rework. – Create well-designed functional interfaces. – Take on harder questions with confidence. GPT-6 Astra combines computer use, asynchronous tool calling, and mid-response steering to handle longer, more involved workflows. See GPT-6 Astra in action:
3:23

Our best model yet: GPT-6 Astra. – Build agents for complex long-running work. – Solve engineering problems with less rework. – Create well-designed functional interfaces. – Take on harder questions with confidence. GPT-6 Astra combines computer use, asynchronous tool calling, and mid-response steering to handle longer, more involved workflows. See GPT-6 Astra in action:

OpenAI Developers

250,016 次观看 • 13 天前

Meet YouArt Workflow on Codex. Your entire creative OS, now running on GPT-6 Astra. AGI has arrived — it’s not evenly distributed.
0:43

Meet YouArt Workflow on Codex. Your entire creative OS, now running on GPT-6 Astra. AGI has arrived — it’s not evenly distributed.

YouArt

169,673 次观看 • 10 天前

HERMES AGENT CAN SHARE MEMORY WITH CODEX AND CLAUDE CODE THROUGH HINDSIGHT. ONE MEMORY BANK. ONE AGENT REMEMBERS, EVERY OTHER AGENT KNOWS. the problem: you use Hermes for orchestration. Codex for coding. Claude Code for debugging. each has its own memory. switch between them and you explain the same project three times. Hindsight fixes this. one shared memory bank that every agent reads and writes to. tell Codex: "the test color for this project is purple." switch to Hermes. ask: "what test color did I pick?" Hermes answers: "purple." no copy-paste. no re-explaining. instant recall. HOW IT WORKS: Hindsight runs as a Docker container on your machine. self-hosted. your data stays local. an LLM powers the memory processing (retain, recall, reflect). RETAIN: extracts facts from your conversations. entities, decisions, preferences, project context. saved to the memory bank automatically. RECALL: when you ask a question, Hindsight pulls from semantic search, keywords, graph connections, and temporal data. fused into one answer. REFLECT: deeper reasoning layer. connects memories across sessions. identifies patterns in your work. produces observations that get smarter over time. CONNECT TO HERMES: Desktop app: Settings → Memory and Context → switch provider from Namosin to Hindsight. set API URL to your local Docker container. set bank ID. done. CLI: hermes memory setup → select Hindsight. verify: hermes memory status should show: provider: hindsight, installed, available. CONNECT TO CODEX: npx hindsight-coding-agents install codex \ --self-hosted --server this installs lifecycle hooks: initialize memory on session start. recall context during work. retain the session when done. enable hooks in Codex: Settings → Hooks → trust all three. CONNECT TO CLAUDE CODE (same command): npx hindsight-coding-agents install all "all" connects every detected agent on your machine. Claude Code, Codex, Cursor, and others. one command. every agent shares the same bank. TAGS FOR FILTERING: every memory gets tagged by harness (Hermes, Codex, Claude Code) and optionally by project name. in the Hindsight control plane: filter by harness. see only Hermes memories. or only Codex memories. or search across everything. soft partitions inside one bank. not hard walls. cross-reference when you need to. ONE BANK OR MANY: one global bank: solo dev, related projects. all agents share everything. patterns emerge across projects. per-project banks: unrelated codebases. each project gets its own memory. no cross-contamination. your call. start with one. split when projects diverge. KNOWLEDGE PAGES (v0.9.0): Hindsight auto-generates living summaries from your accumulated memories. components, concepts, conventions, decisions. not static docs. projected from real agent conversations. auto-refresh as new memories land. WHAT TO KNOW: self-hosted via Docker. your data never leaves your machine. backup system built in (admin CLI + scheduled exports). works with any LLM (local Ollama, OpenAI, Codex subscription). memory defense: redact or block sensitive content automatically. 33,000+ memories accumulated in ~10 days of normal use.
34:12

HERMES AGENT CAN SHARE MEMORY WITH CODEX AND CLAUDE CODE THROUGH HINDSIGHT. ONE MEMORY BANK. ONE AGENT REMEMBERS, EVERY OTHER AGENT KNOWS. the problem: you use Hermes for orchestration. Codex for coding. Claude Code for debugging. each has its own memory. switch between them and you explain the same project three times. Hindsight fixes this. one shared memory bank that every agent reads and writes to. tell Codex: "the test color for this project is purple." switch to Hermes. ask: "what test color did I pick?" Hermes answers: "purple." no copy-paste. no re-explaining. instant recall. HOW IT WORKS: Hindsight runs as a Docker container on your machine. self-hosted. your data stays local. an LLM powers the memory processing (retain, recall, reflect). RETAIN: extracts facts from your conversations. entities, decisions, preferences, project context. saved to the memory bank automatically. RECALL: when you ask a question, Hindsight pulls from semantic search, keywords, graph connections, and temporal data. fused into one answer. REFLECT: deeper reasoning layer. connects memories across sessions. identifies patterns in your work. produces observations that get smarter over time. CONNECT TO HERMES: Desktop app: Settings → Memory and Context → switch provider from Namosin to Hindsight. set API URL to your local Docker container. set bank ID. done. CLI: hermes memory setup → select Hindsight. verify: hermes memory status should show: provider: hindsight, installed, available. CONNECT TO CODEX: npx hindsight-coding-agents install codex \ --self-hosted --server this installs lifecycle hooks: initialize memory on session start. recall context during work. retain the session when done. enable hooks in Codex: Settings → Hooks → trust all three. CONNECT TO CLAUDE CODE (same command): npx hindsight-coding-agents install all "all" connects every detected agent on your machine. Claude Code, Codex, Cursor, and others. one command. every agent shares the same bank. TAGS FOR FILTERING: every memory gets tagged by harness (Hermes, Codex, Claude Code) and optionally by project name. in the Hindsight control plane: filter by harness. see only Hermes memories. or only Codex memories. or search across everything. soft partitions inside one bank. not hard walls. cross-reference when you need to. ONE BANK OR MANY: one global bank: solo dev, related projects. all agents share everything. patterns emerge across projects. per-project banks: unrelated codebases. each project gets its own memory. no cross-contamination. your call. start with one. split when projects diverge. KNOWLEDGE PAGES (v0.9.0): Hindsight auto-generates living summaries from your accumulated memories. components, concepts, conventions, decisions. not static docs. projected from real agent conversations. auto-refresh as new memories land. WHAT TO KNOW: self-hosted via Docker. your data never leaves your machine. backup system built in (admin CLI + scheduled exports). works with any LLM (local Ollama, OpenAI, Codex subscription). memory defense: redact or block sensitive content automatically. 33,000+ memories accumulated in ~10 days of normal use.

YanXbt

29,200 次观看 • 1 个月前

We've just added several new features to Claude Managed Agents. You can now configure effort levels per agent, seed sessions with events, add up to 500 skills per session, use webhooks for environments + memory stores, and stream events for sub-agents.
0:24

We've just added several new features to Claude Managed Agents. You can now configure effort levels per agent, seed sessions with events, add up to 500 skills per session, use webhooks for environments + memory stores, and stream events for sub-agents.

ClaudeDevs

590,373 次观看 • 1 个月前

Computer-use has come a long ways.. This video was entirely recorded, edited, and polished by astra gpt-6 in Codex. The world is not ready for billions of agents needing billions of powerful computers. Until now.
0:57

Computer-use has come a long ways.. This video was entirely recorded, edited, and polished by astra gpt-6 in Codex. The world is not ready for billions of agents needing billions of powerful computers. Until now.

Nick Vasilescu

21,778 次观看 • 7 天前

LLMs are stateless. We built Dria Mem Agent to change that: Making memory a first-class feature. A 4B agent with local interoperable memory across Claude, ChatGPT and LM Studio. It turns LLMs from stateless chat into stateful agents with persistent human-readable memory.
1:03

Sensitive content

LLMs are stateless. We built Dria Mem Agent to change that: Making memory a first-class feature. A 4B agent with local interoperable memory across Claude, ChatGPT and LM Studio. It turns LLMs from stateless chat into stateful agents with persistent human-readable memory.

Dria

170,717 次观看 • 1 年前