This project uses state-memory-mcp with project slug "behavior-mcp" to track tasks, decisions, blockers, and progress. ALWAYS update the state graph when performing work. For the complete tool reference and workflow patterns, see the state-memory-mcp skill in .agents/skills/state-memory-mcp/SKILL.md. <!-- state-memory-mcp:end --> This project utilizes vision-memory-mcp to cache visual states, record layout transitions, provide element grounding, and avoid repetitive LLM vision calls.
2447d agoReviewMountCreate a free account to mount
Teaches the agent to use the state-memory-mcp MCP server to track workflow state, tasks, decisions, blockers, artifacts, plans, milestones, and their semantic relationships in a persistent graph database.
This project tracks workflow state, tasks, design decisions, and blockers using state-memory-mcp with project slug "behavior-mcp". This project utilizes vision-memory-mcp to cache visual states, record layout transitions, provide element grounding, and avoid repetitive LLM vision calls.
2447d agoReviewMountCreate a free account to mount
This project uses behavior-mcp with project slug "behavior-mcp" to execute deterministic behavior trees at ~60Hz in browser runtimes with reactive triggers and safety guardrails.
2447d agoReviewMountCreate a free account to mount
This project uses world-model-mcp with project slug "behavior-mcp" to maintain a persistent 3D/2D spatial internal world model, entity tracking, object permanence, and movement simulation.
2447d agoReviewMountCreate a free account to mount
High-Frequency (~60Hz) In-Browser Behavior Tree Execution Engine for AI Agents @putervision/behavior-mcp executes deterministic behavior trees directly in browser runtimes at 60Hz. It bridges cognitive reasoning decisions with deterministic low-latency action sequences, featuring reactive interrupt triggers, frame recordings, telemetry analytics, and multi-layer safety guardrails. Non-claims statement: Functional agency and closed-loop automation — not consciousness, sentience, or AGI.
2447d agoReviewMountCreate a free account to mount
This project utilizes vision-memory-mcp to cache visual states, record layout transitions, provide element grounding, and avoid repetitive LLM vision calls. To allow cache query and ingestion commands to run automatically without prompting: - Google Antigravity (~/.gemini/config/config.json): Add these rules to your "globalPermissionGrants" -> "allow" list: - "command(vision-memory-mcp)" (Allow running the CLI without parameters prompts) - "read_file(.*\\.gemini/antigravity/brain/.*)" (Allow reading captured screenshots) - "write_file(.*\\.gemini/antigravity/brain/.*)" (Allow saving visual states) - VS Code / Cursor IDE (settings.json): Ensure the agent has execution permissions for…
243mo agoReviewMountCreate a free account to mount
Teaches the agent to use the state-memory-mcp MCP server to track workflow state, tasks, decisions, blockers, artifacts, plans, milestones, and their semantic relationships in a persistent graph database.
Teaches the agent to use the WebCrypt MCP server for AES-256-GCM symmetric encryption, RSA-4096 hybrid encryption, key generation, digital signatures, hashing, and post-quantum cryptography. Includes automated test scripts for exercising all MCP tools.
This project tracks workflow state, tasks, design decisions, and blockers using state-graph-mcp. Before doing any coding or investigation: You MUST update the graph as you work: If the project was just initialized or is missing high-level structure (Plans, Milestones, Decisions): This project utilizes vision-memory-mcp to cache visual states, record layout transitions, provide element grounding, and avoid repetitive LLM vision calls.
243mo agoReviewMountCreate a free account to mount
This project utilizes vision-memory-mcp to cache visual states, record layout transitions, provide element grounding, and avoid repetitive LLM vision calls. This project uses `world-mo
2247d agoReviewMountCreate a free account to mount
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.
putervisionAGENTS.md