Instructions for AI coding agents (Claude Code, Codex, Cursor, etc.) working on this codebase. When working in Conductor, you can use the .context/ directory for scratch notes or agent-to-agent handoff artifacts. This directory is gitignored. The specs/ and docs/ directories are symlinked from external locations. For a fresh clone or new workspace, create these symlinks: These contain private design documents and documentation that are not checked into the repository. This project uses two virtual environments: Use .venv for development tasks…
Steady7 mentions in 2 weeks
No other project uses it yet
43k17mo agoReviewMountCreate a free account to mount
Dash is a self-learning data agent that delivers insights, not just SQL results. It uses a team of specialists (Analyst + Engineer) coordinated by a leader to handle data queries and build computed data assets. Built on Agno. Runs in Slack, the terminal, or the AgentOS web UI.
2.3k7mo agoReviewMountCreate a free account to mount
Scout is an enterprise context agent — a single agno.Agent with N ContextProviders. Ships with WebContextProvider, WorkspaceContextProvider (local files via agno.tools.Workspace), DatabaseContextProvider (the CRM — user's contacts/projects/notes/follow-ups), two WikiContextProviders (a writable knowledge wiki and a read-only voice wiki), SlackContextProvider, GDriveContextProvider, and MCPContextProvider (any MCP server → one querymcp<slug> tool on Scout). GitHub, Gmail, and Calendar land in the next release (were built and verified on the feat/slack-interface branch; dropped from the ship slice until we can test end-to-end with real…
7197mo agoReviewMountCreate a free account to mount
This file provides context for Claude Code when working with this repository. Agentic Investment Team — A multi-agent system built with Agno that simulates a professional investment team deploying $10M into public equities. Demonstrates 5 multi-agent architectures, three-layer knowledge, and institutional learning. All specialist agents use: - Gemini 3 Flash model (gemini-3-flash-preview) - PostgreSQL database (pgvector) for persistence - Committee context (Layer 1) in system prompt - Shared knowledge base (Layer 2) for RAG - Shared learnings (institutional learning) Committee…
1689mo agoReviewMountCreate a free account to mount
A conversational multi-agent team that produces Hyperframes motion-graphics videos from natural-language prompts. Part of the "mini demo agent" family alongside vibe-to-prd. The canonical specification is docs/SPEC.md. All other documentation derives from it — keep the two in sync. - Team definition: vibevideo/team.py (Vibe Video team leader, Coordinate mode) - Member agents: vibevideo/agents/animator.py (Animator), vibevideo/agents/codeexplorer.py (CodeExplorer), vibevideo/agents/researcher.py (Researcher, optional) - Shared settings: vibevideo/settings.py (DB, REPOSDIR, RENDERSDIR, model) - API server: app/main.py (FastAPI + AgentOS web UI) - Custom tools: vibevideo/tools/git.py (GitTools),…
1027mo agoReviewMountCreate a free account to mount
A code companion that lives in Slack. Understands code by searching it directly on disk, reviews PRs and branches, triages issues, learns team conventions, and contributes code via isolated git worktrees. The canonical specification is docs/SPEC.md. All other documentation derives from it. All agents share the same coda_learnings knowledge base via individual LearningMachine instances.
637mo agoReviewMountCreate a free account to mount
This is a thin application over Agno. Keep application wiring and policy here; generic manager behavior belongs in Agno. CLAUDE.md links to this file. - Read the relevant source and inspect git status before editing. Preserve unrelated changes and keep work within the requested scope. - Agno owns OS Manager (os-manager-internal), its members, source tools, Studio, Company Manager (company-manager-internal), authorization, durable execution and sandbox lifecycle. Configure OSManager(root=agentos_root) in app/main.py; do not recreate these components or add application-owned queues, lifecycle code…
Create and register a code-defined agent in this AgentOS from a concrete request or guided discovery, add its UI prompts, reload the development runtime, and verify a real run. Use when the user wants to build or add an agent.
Author eval coverage for an agent in this AgentOS — map what the agent promises, mine real sessions and eval history from Postgres for scenarios, propose capabilities worth testing, then write, run, and audit Case entries in evals/cases.py. Use when the user wants evals created, coverage added, or an agent's behavior pinned down as tests. For failing suites or agent hardening, use improve instead.
Deploy this AgentOS using its own provider instructions, configure JWT verification, and verify the public service. Use for first deployment, redeployment, or production configuration changes.
User-driven loop to change an existing agent in this AgentOS — add a tool/MCP server/toolkit, add a capability (knowledge base, learning/memory, sub-agent, scheduled task), grow the safe Studio registry so components built at runtime gain a new capability, refine its instructions, or fix a specific known bug, verifying each change against the selected development runtime. Use whenever the user names a concrete change to an agent, or wants a new building block available to the platform. For agent hardening without a specific change in mind, use improve.
Harden an existing AgentOS agent or team by finding weaknesses through realistic user simulations, diagnosing their causes, making targeted improvements and verifying more reliable behavior. Use for agent hardening, failing evals, simulation-driven improvement or turning useful scenarios into evals. Also support simulation-only requests. Use create-evals for coverage authoring alone and extend-agent for a specified capability change.
Review this AgentOS repository for public readiness after a refactor or before release. Compare documentation, skills, configuration, component wiring and scripts with the implementation; fix clear documentation drift when requested and report behavioral issues with evidence. Use for a repository consistency sweep, not agent-quality tuning or deployment.
Set up this AgentOS from a fresh clone — confirm Docker, configure .env, boot the containers, prove the MCP endpoint live, connect the AgentOS UI, then build the user's first agent. Use when the user asks to set up the platform, get started, or bring this repo up on a new machine.
Agno docs are direct, concrete, and professional. No marketing fluff. No AI-sounding prose. Every sentence earns its place. We cover a massive surface area. Analogies and commentary add cognitive load…
3859d agoReviewMountCreate a free account to mount
Agno docs are direct, concrete, and professional. No marketing fluff. No AI-sounding prose. Every sentence earns its place. We cover a massive surface area. Analogies and commentary add cognitive load…
3859d agoReviewMountCreate a free account to mount
This file provides context for Codex when working with this repository. AgentOS - A multi-agent demo system built by Agno showcasing Agno framework features (6 agents, 4 teams, 6 workflows, 3 multi-framework agents). All agents share: - PostgreSQL database (pgvector) for persistence - OpenAI GPT-5.4 model (configured in app/settings.py) - Chat history and context management
355mo agoReviewMountCreate a free account to mount
This file provides context for Claude Code when working with this repository. AgentOS - A multi-agent demo system built by Agno showcasing Agno framework features (6 agents, 4 teams, 6 workflows, 3 multi-framework agents). All agents share: - PostgreSQL database (pgvector) for persistence - OpenAI GPT-5.4 model (configured in app/settings.py) - Chat history and context management
355mo agoReviewMountCreate a free account to mount
This file is the source of truth for any agent (Claude Code, Codex, others) working in this repo. CLAUDE.md is a symlink to this file — edit one, both update. AgentOS: the agent platform that powers your product. AgentOS is an agent server built on the Agno framework that turns your agents into a production API attaching to any client: REST API for programmatic use, chat interfaces for humans (Slack is wired in; WhatsApp/Telegram/Discord mirror the same pattern), and MCP…
Plain text files in a repository that tell a coding agent how the project works: commands to run, conventions to follow and things to avoid. CLAUDE.md, AGENTS.md, cursor rules and skills are the common kinds.
CLAUDE.md or AGENTS.md?
CLAUDE.md is read by Claude Code. AGENTS.md is an open format that Codex, Cursor and other agents read. Many projects keep one and point the other at it.
What is a skill?
A folder with a SKILL.md that describes one capability, such as filling PDFs or reviewing code. The agent loads it only when the task calls for it.
Can I search my own team's files too?
Your agents already can, over MCP, limited to the files you're allowed to read. Searching them from this page is coming.
agno-agiCLAUDE.md