Skip to main content
affpapa.org
RU EN
skill Claude Code CX Codex Cursor GitHub Copilot

omni-cache — Claude Code skill: LLM response cache management

Skill for viewing LLM cache statistics, clearing entries, configuring TTL policies, and controlling semantic-similarity caching thresholds. Use it to optimize cache performance and monitor cache state.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓ 
npx skills add cheaper-inference/OmniRoute --skill omni-cache -a claude-code
Open on GitHub

What omni-cache does

omni-cache provides REST API endpoints to manage your LLM response cache. Query detailed statistics across all cache layers, clear individual entries or flush the entire cache, and tune TTL policies and semantic similarity thresholds to fit your workflow.

The skill exposes endpoints like /api/cache for basic stats, /api/cache/stats for detailed information, and /api/cache/entries and /api/cache/reasoning to manage specific cache types. All requests require Bearer token authentication; for local development, you can disable key checks with REQUIRE_API_KEY=false.

Built on OmniRoute, omni-cache integrates with Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, and OpenCode.

What it helps with

  • monitor cache usage and memory footprint in real time
  • clear stale cached responses when they become outdated
  • set different TTL policies for different data types
  • adjust semantic similarity thresholds for cache matching

Example prompts for the agent

  • Show me cache statistics and how much memory is being used
  • Clear all cached model responses
  • Get detailed stats for every cache layer

How to install omni-cache

1Skills CLI (Vercel)

npx skills add cheaper-inference/OmniRoute --skill omni-cache -a claude-code

2Manually: put the files in place

~/.claude/skills/omni-cache/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/omni-cache/

From the same set34

The whole set →
cli-setup cheaper-inference Helps the agent configure OmniRoute, manage autostart, apply CLI updates, and adjust session environment variables. Claude Code CX Codex Cursor +1 1,200installs omni-combos-routing cheaper-inference This skill creates and manages model routing combos with fallback chains, tests, and metrics. Use it when OmniRoute needs configurable provider routing. Claude Code CX Codex Cursor +1 1,200installs omni-inference cheaper-inference Connects OpenAI-compatible inference endpoints for chat, embeddings, audio, and images. Useful for AI agents calling OmniRoute endpoints. Claude Code CX Codex Cursor +1 1,100installs cli-providers cheaper-inference Manage OmniRoute provider connections from the CLI: inspect the catalog, test connections, rotate keys, and view metrics. Useful when provider setup is part of your terminal workflow. Claude Code CX Codex Cursor +1 1,100installs omni-auth cheaper-inference Manage API keys and sessions in OmniRoute. Authenticates requests via Bearer tokens, handles dashboard login with password or OIDC, and controls session access. Claude Code CX Codex Cursor +1 1,100installs cli-routing cheaper-inference Manage model routing combos from the command line with omniroute. Test routing strategies, inspect metrics, and configure fallback chains interactively. Claude Code CX Codex Cursor +1 1,100installs omni-mcp cheaper-inference Connects an agent to the OmniRoute MCP server for request routing, memory, cache, and audit work. Use it when those operations need to be available as MCP tools. Claude Code CX Codex Cursor +1 1,100installs omni-providers cheaper-inference Manages connections to 375 AI providers via REST API: adds keys, tests connections, syncs models. Claude Code CX Codex Cursor +1 1,100installs

Similar

ctx-search mksglu Searches a persistent project knowledge base without reloading source files into context. Queries indexed code, documentation, and session memory via FTS5. Claude Code CX Codex Cursor +1 1,100installs ctx-index mksglu Indexes local files and directories into context-mode's FTS5 database. It allows future searches to pull exact snippets without reloading raw project files into context. Claude Code CX Codex Cursor +1 1,100installs careful garrytan Intercepts Bash and PowerShell commands before execution to catch destructive actions like forced git pushes or database drops. Useful when giving agents terminal access. Claude Code CX Codex Cursor +1 375installs summarize-interview phuryn This skill transforms an interview transcript into a structured report with Jobs to Be Done, satisfaction signals, and action items. Saves time parsing recordings and helps organize insights for product discovery. Claude Code CX Codex Cursor +1 2,800installs setup-matt-pocock-skills Matt Pocock This skill configures a repository for Matt Pocock's engineering skills by setting its issue tracker, triage labels, and domain docs layout. Run it before using the other skills. Claude Code 1,052,851installs to-tickets Matt Pocock Turns a plan, spec, or conversation into small end-to-end tickets with explicit blockers. Use it to agree on the work breakdown before tickets go to a tracker. Claude Code 711,230installs writing-plans Jesse Vincent This skill turns requirements for a multi-step task into an implementation plan before code changes begin. It helps when another engineer needs exact files, interfaces, and checks. Claude Code CX Codex 282,859installs caveman-review JuliusBrussee Turns code review comments into one line per finding: location, problem, fix. Useful when a diff or PR needs a fast pass without the filler. Claude Code CX Codex Cursor +1 410,700installs

Questions about omni-cache

How do I install omni-cache in Claude Code?

Run npx skills add cheaper-inference/OmniRoute --skill omni-cache -a claude-code in your terminal. After installation, the skill is available at ~/.claude/skills/omni-cache/SKILL.md.

What does omni-cache do?

It manages your LLM response cache: displays usage statistics, clears entries, configures TTL policies, and adjusts semantic similarity thresholds to optimize performance.

Is authentication required?

Yes, all requests require a Bearer token obtained via POST /api/auth/login. For local development, set REQUIRE_API_KEY=false to disable the check.

Source text

SKILL.md · MIT 
---
name: omni-cache
description: Manage the LLM response cache. View cache statistics, clear entries, configure TTL policies, and control semantic-similarity caching thresholds.
---
<!-- generated by src/lib/agentSkills/generator.ts; manual edits will be overwritten -->

## Overview

Manage the LLM response cache. View cache statistics, clear entries, configure TTL policies, and control semantic-similarity caching thresholds.

## Authentication

All requests require a valid Bearer token or session cookie. Obtain a token via `POST /api/auth/login` or configure `REQUIRE_API_KEY=false` for local development.

## Endpoints

### GET /api/cache

Get cache statistics

```bash
curl http://localhost:20128/api/cache \
  -H "Authorization: Bearer $OMNIROUTE_TOKEN"
```

### DELETE /api/cache

Clear all caches

```bash
curl -X DELETE http://localhost:20128/api/cache \
  -H "Authorization: Bearer $OMNIROUTE_TOKEN"
```

### GET /api/cache/stats

Get detailed cache statistics

Returns detailed statistics for all cache layers.

```bash
curl http://localhost:20128/api/cache/stats \
  -H "Authorization: Bearer $OMNIROUTE_TOKEN"
```

### DELETE /api/cache/stats

Clear cache statistics

```bash
curl -X DELETE http://localhost:20128/api/cache/stats \
  -H "Authorization: Bearer $OMNIROUTE_TOKEN"
```

### GET /api/cache/entries

GET cache › entries

```bash
curl http://localhost:20128/api/cache/entries \
  -H "Authorization: Bearer $OMNIROUTE_TOKEN"
```

### DELETE /api/cache/entries

DELETE cache › entries

```bash
curl -X DELETE http://localhost:20128/api/cache/entries \
  -H "Authorization: Bearer $OMNIROUTE_TOKEN"
```

### GET /api/cache/reasoning

GET cache › reasoning

```bash
curl http://localhost:20128/api/cache/reasoning \
  -H "Authorization: Bearer $OMNIROUTE_TOKEN"
```

### DELETE /api/cache/reasoning

DELETE cache › reasoning

```bash
curl -X DELETE http://localhost:20128/api/cache/reasoning \
  -H "Authorization: Bearer $OMNIROUTE_TOKEN"
```

## Payloads

See the full OpenAPI specification at `GET /api/openapi/spec` or `docs/openapi.yaml` for detailed request/response schemas.

© cheaper-inference · MIT · cheaper-inference/OmniRoute

See also

Project sponsors

Companies that keep this analytics open
Gold sponsor
Nutra.Club

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor