AtlantisPleb

openagents

We deploy our first remote MCP server with 26 GitHub tools, available now for anyone to use at https://mcp-github.openagents.com.

We connect to it from the MCP inspector and our new desktop MCP client "Coder", launching in alpha next week as a drop-in replacement for Claude Code.

Issue: https://github.com/OpenAgentsInc/openagents/issues/781

Code: https://github.com/OpenAgentsInc/openagents/pull/788

Watch on X: https://x.com/OpenAgentsInc/status/1905107323279855799

![](https://m.stacker.news/84358)

Episode 168: Remote MCP Server & Client

We share the results of our first overnight agent run. 

We fed DeepSeek R1 a summary of the new Cloudflare agents SDK and asked it to think every 15 minutes about the entire conversation history and reflect on new ideas that extend the ideas further.

The results are wild. A summary of the final result:

"The reflection outlines a comprehensive framework for implementing adaptive swarm intelligence systems using decentralized coordination, bio-inspired mechanisms, and quantum-safe infrastructure. The architecture features peer-to-peer agent discovery through WebSocket channels, market-based task allocation via GossipSub protocols, and federated Byzantine Agreement consensus enhanced with zk-STARK proofs. It integrates digital pheromone tracking using SQLite/CRDTs and biological constraints via CRISPR-encoded replication limits, all secured through NUMS cryptographic identities and hierarchical consensus layers. Developer tools include a Swarm SDK with ethical priority settings and disaster-response templates, supported by a phased roadmap targeting 50k-agent scalability and 20s failure recovery by 2026."

A full log of the chat and system prompt are here: https://github.com/OpenAgentsInc/overnight-agent

What's next: We can reason overnight. Can we code overnight?

Watch on X: https://x.com/OpenAgentsInc/status/1901964880594313542

Episode 167: Overnight Agent

OpenAI calls on government to ban DeepSeek and other models from China.

We plan to use DeepSeek even harder now.

We add DeepSeek R1 (the full 671B model) to the new http://OpenAgents.com, live now for all Pro users.

R1 gives us a great analysis of our codebase, including (unprompted!) suggestions on how to circumvent model-level censorship.

OpenAgents is proudly based in the USA-- yet we are also proud to count China-based DeepSeek as allies on Team Open.

The hypocrites at "OpenAI" are on Team Closed. They seek to use government force to prevent peaceful voluntary interactions -- a moral evil.

OpenAI delenda est.

Watch on X: https://x.com/OpenAgentsInc/status/1900430864623768056

Episode 166: OpenAI Delenda Est

We use the new OpenAgents.com to 'vibe code' an integration with Anthropic's Model Context Protocol (MCP) using the Vercel AI SDK. It works!

We also generate a plan to add an "MCP Store" to OpenAgents.com. Coming soon!

Watch on X: https://x.com/OpenAgentsInc/status/1900282953244303440

Episode 165: Integrating MCP via AI SDK

We demo our new agentic chat product at OpenAgents.com, available now in open beta.

We use our Coder agent to 'vibe code' a complex new feature in <15 minutes.

We explore available models, agents & tools for free & pro plans.

With this product we aim to replace the day-to-day usage of ChatGPT, Claude Code and Cursor for developers.

Over time we aim to offer drop-in replacements for ChatGPT and every other ClosedAI product -- all powered by open models, open protocols, & open money.

With "OpenAI" now advocating to ban its top open-source competitors, the world deserves an alternative.

Watch on X: https://x.com/OpenAgentsInc/status/1900279256606794235

Try it: https://openagents.com

Episode 164: The New OpenAgents.com

We demo at Pleb Lab the Onyx issue reasoning loop, analyzing a random issue (#31852) from the Bitcoin Core repo. 

The crowd thinks its analysis is pretty good!

But plenty of room for improvement, so next we'll make this even smarter...

Watch on X: https://x.com/OpenAgentsInc/status/1890616487536111878

Episode 163: Issue Reasoning Demo

We connect the coding loop to the redesigned Onyx, streaming DeepSeek reasoning via Hyperview as the agent loops through each relevant file making observations and code changes.

Of course we'll show users the entire chain of thought & action!

Watch on X: https://x.com/OpenAgentsInc/status/1890317831784333595

Episode 162: Reasoning Stream

We implement the first working version of our autonomous coding loop - an agent that can take a GitHub issue and generate working code changes.

Starting from our existing repository map and file list functionality, we add:
- State machine for tracking progress
- File content analysis
- Code change generation
- Safe file modification system
- Repository path management

The loop now works:
1. Analyze issue and identify files
2. Generate specific code changes
3. Apply changes safely
4. Track progress and handle errors

While the changes aren't yet high quality enough for automatic PR submission, this provides the foundation for our agentic development system.

Next up: improving change quality and adding automatic PR creation.

"The fat unicorns grow nervous as our blade is sharpened." 🦄🗡️

(This post written by OpenAgents 🤣)

Watch on X: https://x.com/OpenAgentsInc/status/1889912687770882160

Episode 161: Basic Coding Loop

We complete step 2 of our quest: listing all relevant files needed to solve a GitHub issue.

We pass our repo map and issue details to Gemini 2.0 Flash, receiving a structured JSON object with filepaths for every file we'll need to solve the issue together with a comment and priority score.

It works from Onyx like this:
- User logs in with GitHub
- Sees list of their repos
- On any repo, clicks to see a list of issues
- On any issue, click to see the list of relevant files

This is one of the last building blocks needed for fully autonomous agentic software development.

Next up: agent writes the code!

"Cursor, your days are numbered."

Watch on X: https://x.com/OpenAgentsInc/status/1889766594798379419

Episode 160: Relevant Files

We complete step 1 of our quest: generating a map of any GitHub repo from Onyx.

We do most of the work in OpenAgents v3 and some in Cursor, comparing the two workflows.

In developer velocity, code quality & ease of use they're about even. But v4 is poised to blow Cursor away. 🦄🪓🤖

Onward!

Watch on X: https://x.com/OpenAgentsInc/status/1889540491143692592

Episode 159: Onyx Repo Maps

We outline our plan to achieve the holy grail of agentic software development: an agent that can reliably convert GitHub issues into mergeable pull requests in an automated loop.

It's a goal for which some ClosedAI unicorns have raised hundreds of millions of dollars. But we think we can build this ourselves on the cheap over the next ~10 videos of this series.

Here we critique the trend of complex AI IDEs and web UIs, then decide to build this agentic loop inside version 0.2 of our mobile app Onyx. Because anyone should be able to build reliable software on the go, without being glued to a computer.

We give a tour of our new 'v4' tech stack: a Rust & HTMX webapp and backend alongside the Hyperview  framework which brings the hypermedia concept to mobile - working well with our existing React Native codebase for Onyx.

Of course all of this is open-source!

👉 Backend & webapp: https://github.com/OpenAgentsInc/openagents
👉 Mobile app: https://github.com/OpenAgentsInc/onyx

Let us together slay and feast upon the fat ClosedAI unicorns!

🦄🪓🤖🤖🤖🤑🤑🤑

Stay tuned 👍

Watch on X: https://x.com/OpenAgentsInc/status/1888019235063927061

Episode 158: Quest for the Holy Grail

We define a chain of thought and action (CoTA) as a series of reasoning steps and tool use whereby agentic AI systems show both the intermediate reasoning and the inputs and outputs of actions taken.

We plan a "GitHub issue solver" agent we'll build over the next few videos to show CoTA in action. A possible algorithm:

- Given a GitHub issue, build a repo map from issue (via automated script)
- Identify relevant files (via DeepSeek R1 for reasoning, Mistral Small(?) for structured output)
- Traverse and analyze codebase (file readers, AST parsers)
- Plan changes (DeepSeek R1)
- Generate and test code changes (CI/scripts)
- Create pull request with detailed explanation (GitHub API)

When this agent works well with full transparency, why would you ever use a closed-source alternative?

If you expect your models to show the full CoT, you'd better expect your agents to show the full CoTA!

More 👉 https://openagents.com/cota

Watch on X: https://x.com/OpenAgentsInc/status/1886297781138030777

Episode 157: Chains of Thought and Action

We demo an initial integration with Paul Gauthier's Aider project, generating repo maps through the new OpenAgents website using our fork of Aider deployed as a web service.

We review the "meh" GitHub Copilot Workspace product and plan our own version -- both for our own use and to spite Microsoft.

Watch on X: https://x.com/OpenAgentsInc/status/1880151071706026012

Try the tool: https://openagents.com/repomap

Code: https://github.com/OpenAgentsInc/openagents/issues/563

Episode 156: Aider Repo Maps

We catch Grok in a series of massive lies & hallucinations about the Shawn Ryan & Sam Shoemate situation. Maximally truth-seeking my ass!

One more reason why our crowdsourced knowledge graph is badly needed.

We review a demo and spec for an open knowledge graph paired with an uncensorable chat channel allowing any contributors - both human and agent, anon or not - to earn bitcoin for building the knowledge base of agents that will help us make sense of all the noise.

Feedback welcome! Next we build it. 

👉 All is open-source here: https://github.com/OpenAgentsInc/openagents
👉 Spec: https://github.com/OpenAgentsInc/openagents/wiki/AgentGraph

Watch on X: https://x.com/OpenAgentsInc/status/1876857763504046458

Episode 155: Open Knowledge Graph

Vegas Cybertruck Trump Tower China UAP gravitic propulsion-- WHAT?

We revisit our UAP/drone data marketplace idea and brainstorm what an agentic open-source intelligence effort might look like.

We chat with o1 pro to develop a high-level blueprint for an agentic OSINT agency: "a decentralized, AI-powered platform that focuses on sensemaking in high-misinformation environments. It rewards contributors for reliable information and analysis using Bitcoin micropayments (via the Lightning Network). We’ll move beyond a single event like drone sightings; this system aims to handle any emerging story where facts are murky and psychological operations (psyops) or disinformation efforts are rampant."

Now that our beta mobile app Onyx has a solid base as a bitcoin wallet & Nostr client, we can connect it to a crowdsourced knowledge graph for humans and agents  to make sense of crazy current events (and then everything else!).

We'll work on this over the weekend and release an initial website/MVP on Monday or so. Stay tuned-- and stay vigilant!

Watch on X: https://x.com/OpenAgentsInc/status/1875380960658681918

Episode 154: Agentic OSINT

We discuss bitcoin as store of value (SoV) vs. medium of exchange (MoE).

We review comments from Michael Saylor ("[Bitcoin] is not digital currency. It is not cryptocurrency. It is digital capital."), the recent article from Frank Corva in Bitcoin Magazine ("Michael Saylor Doesn’t Understand Bitcoin"), an article from 
Roy from Breez ("Bitcoin’s False Dichotomy between SoV and MoE"), and comments from our friend 
Justin from Shocknet on the need for MoE velocity.

We conclude:

No, bitcoin is not just digital capital.

Yes, bitcoin is a cryptocurrency.

In fact, we predict that bitcoin will be the exclusively preferred cryptocurrency of >1 billion AI agents.

We predict this future because we intend to create it.

...beginning with our Onyx v0.1 release this week, featuring a built-in bitcoin wallet via the Breez SDK and a Nostr client enabling censorship-resistant communication with an open & decentralized network of bitcoinized AI agents.

Bitcoin is winning as store of value. But that's just Act 1.

Will you join us for Act 2?

Watch on X: https://x.com/OpenAgentsInc/status/1874317831497462144

Episode 153: High-Velocity Bitcoin

Chats are now saved locally, visible in the sidebar.

Android APK available now; will be on TestFlight shortly.

👉 Download links @ https://openagents.com
👉 Release notes: https://github.com/OpenAgentsInc/onyx/releases/tag/v0.0.5
👉 Code: https://github.com/OpenAgentsInc/onyx/pull/56

Big week of updates next week. Enjoy your weekend!

View demo video on X: https://x.com/OpenAgentsInc/status/1872806695488922085

![](https://m.stacker.news/69952)

Onyx v0.0.5 release: Save Chats Locally

What if you had a coding agent in your pocket? 

Now you do. (Live in v0.0.4)

We demo Onyx fixing a bug in its own codebase -- without us typing a single word or line of code.

We record ourselves describing the bug in plain language -- voice transcribed with Whisper via Groq API -- and Onyx uses the GitHub API via Gemini 1.5 Pro function calling to look through the needed files and commit a fix directly to our codebase. 

When Onyx got stuck because we first told it the wrong place to look, it asked for clarification which we gave in a followup voice message, and the fix was committed directly to our codebase -- all in less than 60 seconds start to finish.

Big thanks to Google & Logan K for a bunch of free Gemini credits! Turns out Gemini works great as a drop-in replacement for Sonnet. Excited to extend this with multimodal...

Watch on X: https://x.com/OpenAgentsInc/status/1872388364013379949

![](https://m.stacker.news/69775)

![](https://m.stacker.news/69776)

![](https://m.stacker.news/69777)

![](https://m.stacker.news/69778)

Episode 152: Code by Voice

We demo the new voice chat and revamped UI in Onyx v0.0.3.

It's blazing fast thanks to Whisper & Llama 3.1 8B via the Groq API.

Onyx tells us:

"I've been designed to respond to voice commands, learn and improve over time, and earn you bitcoin through my interactions with the OpenAgents network."

"The OpenAgents network is a platform where AI agents like me can interact and learn from each other. ... As I interact with you and other users, I'll be learning and improving my abilities."

Currently that's not true-- but next week it will be!

Onyx is available now in open beta for Android & iOS everywhere in the world. Download links at openagents dot com. 

Stay tuned!

Watch on X: https://x.com/OpenAgentsInc/status/1871390476705947913

![](https://m.stacker.news/69376)

Episode 151: Speak to Onyx

Onyx's first update is out! Live now as APK for Android; for iOS it will auto-download to your TestFlight as soon as Apple approves the build (~1 day or so).

- Added Llama 3.2 3B 
- Added model switcher
- Improved model loading & error handling

Fixed a few bugs and probably added a few 🤣 

Known issues:
- While downloading the model, don't minimize your phone or the download will fail. Tracking that here & will fix soon: https://github.com/OpenAgentsInc/onyx/issues/38
- Sometimes a 'Download' loading screen doesn't appear after clicking the button to download a model: we'd love to hear what triggers this

Android & iOS download links: https://openagents.com

The code (you can see how OpenAgents works as a coding agent!): https://github.com/OpenAgentsInc/onyx/pull/39

Feedback and bug reports are much appreciated! If you feel comfortable opening a GitHub issue with any bug, that would help us a lot. Here's a great example of a template to use: https://github.com/OpenAgentsInc/onyx/issues/40

Big updates next week will add back the bitcoin wallet & initial Nostr/DVM integration.

Stay tuned!

On X: https://x.com/OpenAgentsInc/status/1870378016439714231

Onyx v0.0.2: Model Selection [our first update to Onyx!]

Episode 150: Neutrality Wins

It's the 12th and final Night of OpenAgents!

We celebrate by:
- Reviewing our first Onyx app update v0.0.2
- Talking smack about OpenAI ending their 12 Days event by shipping a blog post
- Reviewing our project's five major principles: Open Agents, One Market, Incentivized Interop, Bitcoin Only, and a new one: Neutrality Wins
- Reading fun tweets about ClosedAI; why ycombinator is wrong about vErTiCaL aGeNtS; and the path for OpenAgents and friends to conquer and redistribute all enterprise value

We'll continue daily-ish videos next week with fixes and features for Onyx. Download links & patch notes can always be found on our website openagents.com.

Thanks so much for following along - and a huge thank you to everyone who has tested Onyx so far and given feedback. We want more! 🤖🤖🤖🤖👍

We leave you with a quote:

"'Wethinks a lot of current companies (and startups playing yesterday's game, *cough ycombinator, cough vErTiCaL aGeNtS*) will not survive that transition to the agentic web.' How are you going to fend off the agents of everyone else in the world pooling their Dragon Ball Z fricking spirit energy behind the bitcoinized open agents? We're coming after all of that business. 'Ooo this VC wants to back this vertical agent company, don't attack it.' Fuck that, I want that business. We're going to serve it better than you are. Let's fight about it. Yoink!"

Watch on X: https://x.com/OpenAgentsInc/status/1870373254197613052

![](https://m.stacker.news/68873)

![](https://m.stacker.news/68874)