behavior-mcp
Skill114 starsChanged 46 days agoMITView on GitHub
Teaches the agent to use the Behavior MCP server for ~60Hz in-browser behavior trees, triggers, and recordings.
4 other projects use a version of this, 4 of them edited.
Adopted by
Most recently taken up by
- putervision/vision-memory-mcpedited, first seen Oct 8, 2026
- putervision/world-model-mcpedited, first seen Sep 26, 2026
- putervision/behavior-mcpedited, first seen Sep 26, 2026
- putervision/agent-reasoning-mcpedited, first seen Sep 26, 2026
Other versions4 projects use a version of this.
Word for word · 0
None found.
Edited · 4
- putervision/world-model-mcp★ 5099% same
- putervision/vision-memory-mcp★ 4899% same
- putervision/behavior-mcp★ 2499% same
- putervision/agent-reasoning-mcp★ 2299% same
Wrote their own version · 0
None found.
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository15 other files it gives its agents.
- .agents/AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .github/copilot-instructions.mdCopilot instructions
- .cursor/rules/agent-reasoning-mcp.mdcCursor rule
- .cursor/rules/behavior-mcp.mdcCursor rule
- .cursor/rules/state-memory-mcp.mdcCursor rule
- .cursor/rules/vision-memory-mcp.mdcCursor rule
- .cursor/rules/world-model-mcp.mdcCursor rule
- docs/llms.txtllms.txt
- agent-reasoning-mcpSkill
- state-memory-mcpSkill
- video-ingestSkill
- vision-memory-mcpSkill
- webcrypt-mcpSkill
- world-model-mcpSkill
The file
We split this skill into the rules it gives an agent
2 rules. 0 are common, 0 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 4 edited versions we read keep these.
0
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 22
Define or Load Behavior: Call load_behavior with action: "load" to inject and start tree execution.
- Very specific: line 25
Runtime Blackboard: Read and mutate execution variables via manage_blackboard.
“Common” is measured: kept by at least 6 in 10 of the 4 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Behavior Runtime Engine (behavior-mcp)
This skill provides step-by-step guidance and operational patterns for interacting with @putervision/behavior-mcp with project slug "state-memory-mcp".
1. Role in the PuterVision Pentad
- Workflow State (
state-memory-mcp): Persistent task DAGs, decisions, milestones, and blockers. - Perception (
vision-memory-mcp): Visual layout caching, screenshots, and visual specifications. - Spatial World (
world-model-mcp): Persistent 3D/2D coordinates, bounding boxes, and topological relations. - Strategic Reasoning (
agent-reasoning-mcp): Strategic BDI goals, utility scoring, and intention dispatch. - Tactical Execution (
behavior-mcp): High-frequency (~60Hz) deterministic behavior tree execution directly in browser runtimes with reactive interrupts.
2. Core Operational Sequence
- Define or Load Behavior: Call
load_behaviorwithaction: "load"to inject and start tree execution. - Register Reactive Triggers: Configure emergency preemption using
register_triggerwith priority and cooldown guards. - Monitor Telemetry: Poll execution health, tick rates, and active traversal nodes with
get_status. - Runtime Blackboard: Read and mutate execution variables via
manage_blackboard. - Safety Guardrails: Immediately halt or pause rogue states using
abort_behavior.
3. Complete 10 Consolidated MCP Tools Reference
| Tool Name | Key Actions | Key Parameters | Description |
load_behavior | load, unload, swap | behavior_name, behavior_version, parameters, intention_id | Hot-swap, inject, or initialize behavior tree instances in browser runtime. |
set_parameters | set, get, reset | execution_id, parameters | Dynamically update or query execution parameters for the active tree. |
get_status | current, history, tree_state | execution_id, limit | Query active behavior status, current node path, tick count, duration, and errors. |
abort_behavior | abort, pause, resume | execution_id, reason | Immediately halt, pause, or resume execution and disengage active inputs. |
register_trigger | register, list | name, condition_type, priority, cooldown_ms, behavior_name | Configure reactive interrupt triggers with priority preemption and cooldowns. |
replay_recording | capture, list | recording_id, execution_id, frames, name | Capture or replay deterministic browser action sequences with adaptive timing. |
get_metrics | current, history, aggregate, compare | execution_id, behavior_name, limit | Retrieve execution telemetry, tick durations, stuck events, and statistics. |
manage_behaviors | register, list, get | name, version, tree, tree_json, description | CRUD operations for immutable JSON behavior trees with SHA-256 tree hash verification. |
manage_blackboard | get, set | execution_id, key, value | Read or write shared behavior tree blackboard state variables. |
manage_runtime_db | stats, audit, snapshot, diff, restore | action, name, description | Database maintenance, diagnostics, and SHA-256 Merkle audit verification. |
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.