Open Source AI Live
Key Takeaways
Live coding and demonstration of open source AI and real agent workflows using Codex stream setup and DotAgents voice control
Original Description
Live with AJ from TechFren.
Today we're digging into open source AI and real agent workflows: Codex stream setup, DotAgents voice control, Hermes Agent, OpenClaw, browser automation benchmarks, Playwright MCP, Wordle as a test harness, and a live Tailscale RTMP clipping pipeline.
We move fast across GitHub projects, Codex issues, local model safety, agent control panels, voice agents, repo security checks, vector databases, and live clip infrastructure.
TIMESTAMPS
0:00 - Open source intro
3:34 - Stream dashboards
6:56 - Codex set up stream
9:48 - Hermes dashboard workflow
11:18 - Codex browser control
12:25 - OBS CLI and AI careers
18:21 - CrewAI updates
20:07 - Harnesses matter
23:11 - Local model safety
27:59 - Codex hotkey request
29:57 - DotAgents voice demo
33:28 - Codex iOS plugin
34:57 - Terminal bench question
40:32 - Chaos Coder demo
43:56 - Securing env secrets
47:10 - Feature request copy
1:09:51 - Codex token usage
1:13:04 - Alex idea radar
1:17:05 - Speech-to-speech repo
1:28:52 - Agent control panels
1:31:53 - Hermes neural map
1:35:49 - Cmux and Herder
1:41:04 - Canvas voice agents
1:44:07 - OpenClaw vs Hermes
1:48:43 - Importing Hermes skills
1:54:08 - Chrome DevTools angle
1:54:11 - OpenClaw install plan
1:58:12 - Token pricing critique
2:00:53 - OpenClaw voice setup
2:09:12 - Repo safety checks
2:15:39 - ZVec vector database
2:20:17 - Browser agent benchmark
2:28:12 - Playwright MCP bloat
2:30:35 - Wordle bench
2:38:32 - Playwright token costs
2:39:47 - Live clipping idea
2:45:01 - Custom RTMP plan
2:50:10 - Hermes RTMP server
2:52:24 - Sub-agent orchestration
2:57:01 - YouTube poll design
3:14:09 - Live clip dashboard
3:15:17 - Tailscale RTMP ingest
3:16:54 - First live clip
3:21:08 - Clips transcript dashboard
3:23:26 - Agent desktop idea
3:25:11 - Stream wrap-up
TechFren: https://techfren.net
Subscribe for grounded AI builds, open source AI tools, local model workflows, agent experiments, and practical tech breakdowns.
Watch on YouTube ↗
(saves to browser)
Sign in to unlock AI tutor explanation · ⚡30
More on: Agent Foundations
View skill →
Related Reads
📰
📰
📰
📰
We just published a detailed investigation into whether AI agent skills can push
Dev.to · Carlos Casalicchio
I Built a Runtime Immune System for Multi-Agent AI — Here’s What Broke First 🛡️
Dev.to · nithiya-rajesh
AWS Self-Healing Infrastructure: Catching and Fixing Server Crashes with AI Autopilot
Medium · AI
CLI Ownership Management: master, owner, and session Commands for Self-Hosted Wallets
Dev.to AI
Chapters (46)
Open source intro
3:34
Stream dashboards
6:56
Codex set up stream
9:48
Hermes dashboard workflow
11:18
Codex browser control
12:25
OBS CLI and AI careers
18:21
CrewAI updates
20:07
Harnesses matter
23:11
Local model safety
27:59
Codex hotkey request
29:57
DotAgents voice demo
33:28
Codex iOS plugin
34:57
Terminal bench question
40:32
Chaos Coder demo
43:56
Securing env secrets
47:10
Feature request copy
1:09:51
Codex token usage
1:13:04
Alex idea radar
1:17:05
Speech-to-speech repo
1:28:52
Agent control panels
1:31:53
Hermes neural map
1:35:49
Cmux and Herder
1:41:04
Canvas voice agents
1:44:07
OpenClaw vs Hermes
1:48:43
Importing Hermes skills
1:54:08
Chrome DevTools angle
1:54:11
OpenClaw install plan
1:58:12
Token pricing critique
2:00:53
OpenClaw voice setup
2:09:12
Repo safety checks
2:15:39
ZVec vector database
2:20:17
Browser agent benchmark
2:28:12
Playwright MCP bloat
2:30:35
Wordle bench
2:38:32
Playwright token costs
2:39:47
Live clipping idea
2:45:01
Custom RTMP plan
2:50:10
Hermes RTMP server
2:52:24
Sub-agent orchestration
2:57:01
YouTube poll design
3:14:09
Live clip dashboard
3:15:17
Tailscale RTMP ingest
3:16:54
First live clip
3:21:08
Clips transcript dashboard
3:23:26
Agent desktop idea
3:25:11
Stream wrap-up
🎓
Tutor Explanation
DeepCamp AI