omni-cache
GitHub管理LLM响应缓存,支持查看统计、清除条目、配置TTL策略及语义相似度阈值。提供REST API接口进行缓存状态监控与管理,适用于优化大模型调用性能与资源消耗的场景。
Trigger Scenarios
Install
npx skills add diegosouzapw/OmniRoute --skill omni-cache -g -y
SKILL.md
Frontmatter
{
"name": "omni-cache",
"description": "Manage the LLM response cache. View cache statistics, clear entries, configure TTL policies, and control semantic-similarity caching thresholds."
}
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
curl http://localhost:20128/api/cache \
-H "Authorization: Bearer $OMNIROUTE_TOKEN"
DELETE /api/cache
Clear all caches
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.
curl http://localhost:20128/api/cache/stats \
-H "Authorization: Bearer $OMNIROUTE_TOKEN"
DELETE /api/cache/stats
Clear cache statistics
curl -X DELETE http://localhost:20128/api/cache/stats \
-H "Authorization: Bearer $OMNIROUTE_TOKEN"
GET /api/cache/entries
GET cache › entries
curl http://localhost:20128/api/cache/entries \
-H "Authorization: Bearer $OMNIROUTE_TOKEN"
DELETE /api/cache/entries
DELETE cache › entries
curl -X DELETE http://localhost:20128/api/cache/entries \
-H "Authorization: Bearer $OMNIROUTE_TOKEN"
GET /api/cache/reasoning
GET cache › reasoning
curl http://localhost:20128/api/cache/reasoning \
-H "Authorization: Bearer $OMNIROUTE_TOKEN"
DELETE /api/cache/reasoning
DELETE cache › reasoning
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.
Version History
-
d804179
Current 2026-10-19 14:21
将API端点的基础URL从https://localhost更改为http://localhost,以适配本地开发环境的安全配置要求。
-
ba597b6
2026-09-09 13:20
文档化所有已实现的OpenAPI路由,覆盖692个路径;重新生成18个Agent技能文件以同步最新API规范。
- 1cafd32 2026-07-25 11:47


