Christopher David's avatar
Christopher David
npub1tlv6...7fdm
Founder, OpenAgents
Christopher David's avatar
Christopher David 1 year ago
Episode 118: Version Two We say goodbye to ChatGPT, Claude, Copilot & Cursor! We introduce version 2 of OpenAgents: your all-in-one productivity dashboard. v2 includes: ➡️ Chat with top AI models ➡️ Multiple simultaneous chats in draggable/resizable windows ➡️ Deep integration with any GitHub codebase: create/edit files, smart search via @greptileai, open pull requests ➡️ Web scraping via @firecrawl_dev ➡️ Pay-as-you-go via Stripe or Bitcoin ⚡️ 👆That all goes live to the public on Monday, August 12. And coming soon: ➡️ File uploads ➡️ Voice commands ➡️ Long-term agent memory ➡️ Long-running agents ➡️ Third-party plugins ➡️ Agent Store ➡️ Rev-share referrals ➡️ Making all Microsoft products irrelevant starting with Copilot, VSCode & GitHub Stay tuned!
Stacker News
Episode 118: Version Two \ stacker news ~openagents
Watch on X: https://x.com/OpenAgentsInc/status/1821751383227347101 We say goodbye to ChatGPT, Claude, Copilot & Cursor! We introduce version 2 of O...
Christopher David's avatar
Christopher David 1 year ago
Episode 114: Planning & Execution We upgrade AutoDev's planning to include additional context from past memories and relevant files. AutoDev executes the plan over 20+ steps, using the following nine tools to make meaningful code changes while learning over time. Next up, submitting pull requests to GitHub! - view_hierarchy - View file/folder hierarchy at path - view_file - View file contents at path - find_files - Find relevant files to query - remember_insights - Perform a similarity search on previously recorded insights - query_files_by_vector - Query files by vector similarity based on their summaries - generate_plan - Generate a multi-step plan for complex tasks. - retrieve_memories - Retrieve relevant memories from the memory stream - add_memory - Add a new memory to the memory stream - reflect_on_codebase - Generate higher-level insights about the codebase
Stacker News
Episode 114: Planning & Execution \ stacker news ~openagents
We upgrade AutoDev's planning to include additional context from past memories and relevant files. AutoDev executes the plan over 20+ steps, using ...
Christopher David's avatar
Christopher David 1 year ago
Episode 113: Agent Memories & Reflections We use AutoDev to implement the memory, retrieval and reflection systems from the Generative Agents paper. This will enable AutoDev and all other OpenAgents to build deep knowledge about any codebase or corpus of data.
Stacker News
Episode 113: Agent Memories & Reflections \ stacker news ~openagents
We use AutoDev to implement the memory, retrieval and reflection systems from the Generative Agents paper. This will enable AutoDev and all other O...
Christopher David's avatar
Christopher David 1 year ago
Episode 112: Using AutoDev We review our new AutoDev product and use it to build a 3D canvas for a knowledge graph of codebase insights. Watch on X:
X (formerly Twitter)
OpenAgents (@OpenAgentsInc) on X
Episode 112: Using AutoDev We review our new AutoDev product and use it to build a 3D canvas for a knowledge graph of codebase insights.
Stacker News
Episode 112: Using AutoDev \ stacker news ~openagents
We review our new AutoDev product and use it to build a 3D canvas for a knowledge graph of codebase insights. Watch on X: https://x.com/OpenAgentsI...
 image
Christopher David's avatar
Christopher David 1 year ago
Episode 111: Heads-Up Display We give AutoDev a heads-up display (HUD). We use voice (via Groq) to search over our codebase with natural language (via Greptile), seeing a summary of each file in a separate HUD pane. image - Watch on X:
X (formerly Twitter)
OpenAgents (@OpenAgentsInc) on X
Episode 111: Heads-Up Display We give AutoDev a heads-up display (HUD). We use voice (via @GroqInc) to search over our codebase with natural lang...
 - SN:
Stacker News
Episode 111: Heads-Up Display \ stacker news ~openagents
We give AutoDev a heads-up display (HUD). We use voice (via Groq) to search over our codebase with natural language (via Greptile), seeing a summar...
 - Groq:
Groq
Groq is fast, low cost inference.
The Groq LPU delivers inference with the speed and cost developers need.
 - Greptile:
Greptile
AI Code Review - Greptile | Merge 4X Faster, Catch 3X More Bugs
AI Code Reviews that understand your entire codebase. Automate PR reviews, catch bugs faster, improve code quality with AI-driven analysis. Try Gre...
Christopher David's avatar
Christopher David 1 year ago
Episode 107: Codebase Indexing via Greptile We write an Extism plugin for Greptile and consume it via our new Golang/HTMX frontend for AutoDev. Claude Artifacts makes it fast! - Greptile Extism plugin:
GitHub
GitHub - OpenAgentsInc/plugin-greptile: Greptile Extism plugin
Greptile Extism plugin. Contribute to OpenAgentsInc/plugin-greptile development by creating an account on GitHub.
 - AutoDev UI: https://github.com/OpenAgentsInc/autodev - Greptile:
Greptile
AI Code Review - Greptile | Merge 4X Faster, Catch 3X More Bugs
AI Code Reviews that understand your entire codebase. Automate PR reviews, catch bugs faster, improve code quality with AI-driven analysis. Try Gre...
 - Extism:
Extism - make all software programmable. Extend from within. | Extism - make all software programmable. Extend from within.
Extism is the open source, universal plug-in system. Extend all the software everywhere! Powered by WebAssembly.
X (formerly Twitter)
OpenAgents (@OpenAgentsInc) on X
Episode 107: Codebase Indexing via Greptile We write an @extism plugin for @greptileai and consume it via our new Golang/HTMX frontend for AutoDev...
Christopher David's avatar
Christopher David 1 year ago
Episode 106: Brainstorming Agentic Artifacts We review a demo AutoDev+WANIX UI generated by Claude Artifacts. We explore Claude's new Artifacts & Projects UI and brainstorm how to extend OpenAgents in this direction, building on our open-source extensibility via agent plugins.
X (formerly Twitter)
OpenAgents (@OpenAgentsInc) on X
Episode 106: Brainstorming Agentic Artifacts We review a demo AutoDev+WANIX UI generated by Claude Artifacts. We explore Claude's new Artifacts &...
Christopher David's avatar
Christopher David 1 year ago
Episode 105: Reaction: Progrium Technology Thesis We learn more about the philosophy behind WANIX and react to the thesis video from its creator @progrium. With a big emphasis on reusable/extensible building blocks, WANIX and the broader Tractor ecosystem seem to dovetail well with our WASM-based agent plugin system. Can we use this for AutoDevs? - Original video & transcript:
progrium technology company
Progrium Technology Thesis
Creating software is too complicated. Our options are overwhelming, our tooling is too bloated, and things rarely ever just work.
 - Progrium github: github.com/progrium - Tractor github: github.com/tractordev - WANIX site: wanix.sh - WANIX github: github.com/tractordev/wanix
X (formerly Twitter)
OpenAgents (@OpenAgentsInc) on X
Episode 105: Reaction: Progrium Technology Thesis We learn more about the philosophy behind WANIX and react to the thesis video from its creator @...
Christopher David's avatar
Christopher David 1 year ago
Episode 103: Planning AutoDev Agents We plan a new category of agents called AutoDevs. With our core building blocks in place -- chat UI, Agent Store, bitcoin rev-share, and plugins UI -- we are ready to build the first truly compelling agents. Goodbye Devin, hello AutoDevs.
Stacker News
Episode 103: Planning AutoDev Agents \ stacker news ~openagents
We plan a new category of agents called AutoDevs. With our core building blocks in place -- chat UI, Agent Store, bitcoin rev-share, and plugins UI...
Christopher David's avatar
Christopher David 1 year ago
Episode 102: Agent Plugins UI We extend our agent marketplace with an interface to connect custom plugins to agents. Plugins are written by community developers in any of eight programming languages, compiled to WASM via Extism, and attached to agents with an optional fee to the plugin developer paid in #bitcoin over Lightning. ⚡️ The world's first AI agent marketplace with agent builder payouts every minute now ALSO allows developers to upgrade agents with custom functionality. It's about to get interesting! Docs:
Page Not Found
 Try it:
OpenAgents
 (Plugins functionality is in beta and may be buggy! Please tweet at us any bugs or unexpected behavior :)
Stacker News
Episode 102: Agent Plugins UI \ stacker news ~openagents
Watch on X: https://x.com/OpenAgentsInc/status/1800665114573521029 We extend our agent marketplace with an interface to connect custom plugins to a...
Christopher David's avatar
Christopher David 1 year ago
Episode 100: Looking Ahead We review our updated 2024 roadmap. Launched so far: ✅ Chat UI (agents & ~15 top LLMs) ✅ Agent Builder ✅ Agent Store with rev-share paid every minute Launching in June: 🔳 Plugins UI - Agent builders can upgrade their agents using plugins written by developers who earn a share of revenue 🔳 Profiles, posts, referrals - Social features for easy sharing & discoverability of agents 🔳 Developer API - Control agents programmatically Later in 2024: 🔳 Mobile app - One app to control your personal fleet of agents 🔳 Self-serve platform for businesses - The easiest way for small businesses to use top agents in production 🔳 Frontier lab - We'll build the world's #1 lab for applied AI: open source, open science, and truly open AI. Stay tuned!
Stacker News
Episode 100: Looking Ahead \ stacker news ~openagents
Watch on X: https://x.com/OpenAgentsInc/status/1798870330418831627 We review our updated 2024 roadmap. Launched so far: ✅ Chat UI (agents & ~15 t...
 image
Christopher David's avatar
Christopher David 1 year ago
Craft HackAIthon entry: Magency, a Nostr client for AI agents There is no good way to control AI agents on a mobile phone. There should be an app for that! Magency is a mobile app that lets you "make a wish", aka just say what you want into one text box and see a feed of updates from your agents working. Our backend has an agentic loop based on the new "intelligent go-explore" algorithm which improves on the usual brittleness of 'chain of thought' agentic loops. More on IGE here:
arXiv.org
Intelligent Go-Explore: Standing on the Shoulders of Giant Foundation Models
Go-Explore is a powerful family of algorithms designed to solve hard-exploration problems built on the principle of archiving discovered states, an...
 We combine IGE with a new idea: what if agents can access a shared global archive of events - so they can learn from each other - as well as a shared global skill library? The app's feed of updates is a stream of Nostr events using new event kinds based on IGE: 38000 (wish = agent goal), 38001 (archive), 38002 (action taken). Magency was an attempt to square the circle of: 1) a consumer-facing UX for controlling multiple agents, 2) a decentralized architecture enabling an open ecosystem of extensible agents that interoperate and evolve. A bit too ambitious for a 24-hour hackathon, but we are excited to fold these ideas into OpenAgents.
Stacker News
Magency - Mobile app / Nostr client - HackAIthon entry \ stacker news ~openagents
Demo video on X: https://x.com/AtlantisPleb/status/1798730530374230312 There is no good way to control AI agents on a mobile phone. There should be...
 Demo video on X:
X (formerly Twitter)
Christopher David (@AtlantisPleb) on X
Magency: my project for the @craft_ventures agents hackathon 🤖👇 There is no good way to control AI agents on a mobile phone. There should be...
↑