# Resource Allocator

Resource Allocator manages agent swarm capacity through adaptive resource distribution and predictive scaling across CPU, memory, storage, and network channels.

- subagent · `type=agent` · Claude Code, Codex, Cursor · ★ 850 repo stars
- Author: ruvnet
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/ruvnet/agentic-flow/tree/HEAD/.claude/agents/optimization/resource-allocator.md
- Updated: 2026-10-26
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/agents/resource-allocator

## What it does

The subagent coordinates hardware allocation for agent swarms. It evaluates memory, compute, disk, and network constraints against active workloads. By parsing temporal metrics over selectable time windows, it isolates baseline usage, cyclical surges, and anomalous spikes, then solves trade-offs using a multi-objective genetic algorithm.

Capacity forecasting uses an ensemble setup: LSTM sequences for time-series projection, Random Forest regressors, Isolation Forest for outlier detection, and Deep Q-Network reinforcement learning. The system validates models during execution and commits them to disk only if accuracy clears the 0.85 benchmark.

Neural model updates rely on runtime MCP methods `neural_train` and `model_save`. If those MCP actions are missing from the environment, predictive retraining will fail to run.

## Install

### Claude Code (native platform)

**Manually: put the files in place**
- File: `.claude/agents/resource-allocator.md` — For all projects use ~/.claude/agents/. Claude delegates by the description field or an @-mention

### Codex

**Manually: put the files in place**
- File: `.codex/agents/resource-allocator.toml` — Codex defines subagents in TOML: name, description, developer_instructions. Move the Markdown text into developer_instructions by hand. For all projects use ~/.codex/agents/

### Cursor

**Manually: put the files in place**
- File: `.cursor/agents/resource-allocator.md` — Cursor also reads .claude/agents/

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/ruvnet/agentic-flow/tree/HEAD/.claude/agents/optimization/resource-allocator.md

## When to use it
- optimize CPU and memory distribution across concurrent agent swarms
- predict upcoming workload spikes using trained LSTM models
- isolate anomalous resource usage patterns from weekly historical trends
- generate balanced allocation plans via Pareto front genetic solvers

## Example prompts
- Analyze current swarm usage and generate an adaptive resource allocation plan
- Inspect workload metrics for anomalous spikes across the last seven days
- Run scaling prediction for the next 3600 seconds with 0.95 confidence

## Similar
- [performance-analysis](https://affpapa.org/en/nevibecode/skills/performance-analysis.md) — skill · 1200 installs
- [qdrant-scaling](https://affpapa.org/en/nevibecode/skills/qdrant-qdrant-scaling.md) — skill · 1500 installs
- [qdrant-sizing](https://affpapa.org/en/nevibecode/skills/qdrant-sizing.md) — skill · 222 installs
- [render-scaling](https://affpapa.org/en/nevibecode/skills/render-scaling.md) — skill · 416 installs
- [cto-review](https://affpapa.org/en/nevibecode/skills/cto-review.md) — skill · 399 installs
- [thinking-margin-of-safety](https://affpapa.org/en/nevibecode/skills/thinking-margin-of-safety.md) — skill · 649 installs

From the same set: [ruvnet/agentic-flow](https://affpapa.org/en/nevibecode/by/ruvnet/agentic-flow.md) — 76 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
