No-Code Agentist

The First Agentic Trading Interface. @minara AI refers to itself as the first "agentic" trading interface, because it shifts from standard, passive trading tools to an active, autonomous ecosystem. Traditional interfaces require you to look at charts, jump between tabs, formulate a plan and manually execute a trade. Minara redefines this by closing the entire loop from insight to action within a single, natural language flow. The 3 Pillars of an Agentic Interface. 1. The Closed-Loop Flow: Insight → Decision → Execution. Standard trading requires a fragmented workflow users check social feeds for sentiment, analyze on-chain wallet movements on an explorer and jumping to a centralized or decentralized exchange to execute. Minara consolidates this into one terminal or chat window; → Analysis: You can ask it to analyze real-time market data, look into whale wallet behaviors or cross-reference sentiment signals. → Recommendation: It translates complex on-chain or macro data into a structured investment plan. → Execution: With a single prompt, it utilizes secure smart wallets with account abstraction to handle cross-chain routing and instantly place the trade. 2. Conversational Quant Strategies (Set and Forget) Instead of forcing you to write code or configure complex parameter dashboards, Minara lets you build automated, rule-based trading workflows using plain text. The agent builds the workflow, backtests the logic, visualizes the metrics and deploys it. 3. Autopilot Mode with Multi-Wallet Safety. When you turn Autopilot on for a specific sub-wallet, the AI agent takes full control of that wallet's designated trading strategy. To prevent human-machine interference, the interface blocks manual order placement on that specific wallet while the AI is executing its strategy, ensuring the automated system can manage risk parameters, stop-losses and take-profits natively without conflicting signals. Minara moves the friction of gas fees, cross-chain bridging and manual key management with an agentic interface that turns the user from an operator into a manager. You no longer manage the execution details, you are direct to the strategy, while the AI agent navigates the underlying multi-chain financial rails.

Swarmcore isn't just another AI agent framework. It's a Postgres-native AI swarm orchestration platform built for production. ⚡ Config-driven multi-agent workflows (no code) ⚡ Parallel execution with specialized AI agents ⚡ Built-in memory & observability ⚡ ACID-backed agent coordination on PostgreSQL ⚡ Deploy once, interact from Telegram, Slack, Discord, WhatsApp, Signal, Email & Web While a single AI agent works sequentially, a Swarmcore swarm plans, codes, tests, and deploys in parallel—24/7. Wake up to features shipped, bugs fixed, and staging already deployed. The future isn't one AI assistant. It's autonomous AI teams working together. Follow us : https://t.co/L9YwN05NUh Test our app : https://t.co/emCGqUJMqq #AI #MultiAgent #AgenticAI #PostgreSQL #OpenSource #LLM #DevTools #AIEngineering #Swarmcore

Andrej Karpathy stopped using AI to write code. The co-founder of OpenAI. The man who built Tesla's Autopilot vision team from scratch. The person who coined the term "vibe coding." In April 2026, he announced that a large fraction of his LLM token budget was no longer going into manipulating code, it was going into manipulating knowledge. Then he published a single markdown file on GitHub explaining what he had built instead. It got 17 million views. 13,000 GitHub stars. Dozens of community implementations within a week. He called it the LLM Wiki. And the idea behind it is so simple it is almost embarrassing that nobody published it sooner. Here is the problem it solves. Most people's experience with LLMs and documents looks like RAG you upload a collection of files, the LLM retrieves relevant chunks at query time, and generates an answer. This works. But the LLM is rediscovering knowledge from scratch on every question. There is no accumulation. Ask a subtle question that requires synthesizing five documents, and the LLM has to find and piece together the relevant fragments every time. Nothing is built up. NotebookLM works this way. ChatGPT file uploads work this way. Most RAG systems work this way. Every session starts from zero. The AI never learns the territory. It just searches it again. Karpathy's pattern is the opposite. Instead of retrieving from raw documents every time, the LLM builds and maintains a persistent, structured wiki — and answers questions from the compiled knowledge rather than the raw fragments. Here is how the architecture works. Three layers. Layer 1 — Raw sources. Your curated documents. Articles, papers, PDFs, meeting notes, screenshots. These are immutable — the LLM reads them but never modifies them. This is your source of truth. The moment you start editing raw files by hand, you have two systems of record and no way to tell which one is true. Layer 2 — The wiki. A directory of LLM-generated markdown files. Summaries, entity pages, concept pages, comparisons, a master index, a chronological log. The LLM owns this layer entirely. It creates pages, updates them when new sources arrive, maintains cross-references, and keeps everything consistent. You read it. The LLM writes it. Layer 3 — The schema. A CLAUDE.md or AGENTS.md file that tells the LLM how the wiki is structured, what conventions to follow, and what workflows to run. This is the config that turns a generic chatbot into a disciplined wiki maintainer. Karpathy's phrase captures the whole thing: "Obsidian is the IDE. The LLM is the programmer. The wiki is the codebase." Here is what happens when you drop a new source into the system. You save an article into raw/. You tell the LLM to ingest it. The LLM reads the source, writes a summary page, updates the master index, creates or updates entity pages for every person, company, or concept mentioned, creates or updates concept pages for every idea, adds cross-references between related pages, and logs the ingest in the activity record. A single source might touch 10 to 15 wiki pages. This is the bookkeeping that humans abandon — filing, cross-referencing, updating related entries, noting contradictions. The exact work that kills every personal knowledge system you have ever started. The LLM does it tirelessly. Every time. Without forgetting. Here is the key distinction from RAG. RAG re-derives an answer from raw chunks on every query and accumulates nothing. The LLM Wiki compiles sources into structured, linked pages once — and questions are answered from that built artifact. The analogy: raw/ is source code, wiki/ is the compiled executable. Knowledge that is compiled is retrieved. Knowledge that is not is rediscovered from scratch. And here is the rule Karpathy emphasizes most. Lint the knowledge. Treat the wiki like code and run health checks. Ask the model to find contradictions between pages, surface low-confidence claims, list orphan pages, and flag entities that drifted into two spellings. A contradiction is information — it means two sources disagree and now you know where to look. Skipping the lint is how a wiki quietly rots while the graph still looks impressive. Start small. Begin with ten sources, not ten thousand. Get ingest, query, and lint to feel natural before you add complexity. The first few ingests will be messy. Naming conventions will change. That is normal. A small wiki you actually use beats a beautiful architecture you abandon in week three. The community response tells you how much this resonated. Within a week of Karpathy's gist, the community produced dozens of implementations full Python agents, Obsidian integrations, wiki compilers, web interfaces. The pattern works with Claude Code, Codex, OpenCode, Gemini CLI, and any LLM agent that can read and write files. You do not need any of them. The entire system works with nothing but an LLM agent and a file system. Paste the pattern into your CLAUDE.md and Claude Code becomes your wiki maintainer. Here is why this matters more than another AI tool. Every personal knowledge system you have ever tried Notion, Evernote, Roam, Obsidian, died the same way. Not because the tool was bad. Because the maintenance was unsustainable. The filing. The tagging. The cross-referencing. The updating when new information arrived. The bookkeeping that makes a knowledge base useful is the exact work nobody wants to do. Karpathy's insight is that the bookkeeping is exactly what LLMs are good at. Tirelessly reading, summarizing, filing, linking, updating, and maintaining consistency — without getting bored, without forgetting, without deciding it is too tedious and abandoning the project in week four. You curate sources and ask questions. The LLM does the bookkeeping. The wiki compounds over time every source you add and every question you ask makes it richer. The tedious part of maintaining a knowledge base is not the reading or the thinking. It is the bookkeeping. And the bookkeeping just got automated. Source: Andrej Karpathy · GitHub Gist · AI Builder Club · Vanja. io · MindStudio · April 2026 ( Link in the comments)

vm0 / Zero — the "AI teammate" that lives in your Slack and actually does real work. Not another agent framework. Not another chatbot. Zero is a self-hosted, 100+ tool-integrated AI worker you @mention in Slack and hand real roles to. What sets it apart from the dozens of agent platforms out there: - It's opinionated about *outcomes*, not workflows. You say "morning brief" — it pulls Calendar, Linear, Slack, and X into one digest and delivers it before standup. No drag-and-drop node editor required. - It resolves identity. "My PRs," "assign to me" — Zero knows who you are across GitHub, Slack, and Linear automatically. This matters more than it sounds like. - 100+ integrations out of the box: Gmail, Notion, Sentry, Linear, HubSpot, Figma, Vercel, Intercom, Axiom, DocuSign, and more. - Runs in isolated Firecracker microVMs. Credentials never leave the sandbox. Fully auditable. - Open source (this repo). Inspect it, fork it, self-host it. The use cases it ships with are practical: inbox triage, tech debt scanning, KOL research, bug filing from Slack threads, investor update drafting, meeting digest → action items, employee onboarding. This is the "Claude Code for the whole company" bet — not just coding, but ops, research, outreach, reporting. And it's 1,100+ stars and growing fast. https://t.co/R9EG3eq7Jd