{"data":{"slug":"dragonflydb-dragonfly","name":"dragonfly","tagline":"A modern replacement for Redis and Memcached","github_url":"https://github.com/dragonflydb/dragonfly","owner":"dragonflydb","repo":"dragonfly","owner_avatar_url":"https://avatars.githubusercontent.com/u/104819355?v=4","primary_language":"C++","stars":31018,"forks":1230,"topics":["cache","cpp","database","fibers","in-memory","in-memory-database","key-value","keydb","memcached","message-broker","multi-threading","nosql","redis","valkey","vector-search"],"archived":false,"github_pushed_at":"2026-08-22T08:55:03+00:00","maintenance_label":"Very active","stars_delta_30d":115,"url":"https://www.graphcanon.com/tools/dragonflydb-dragonfly","markdown_url":"https://www.graphcanon.com/tools/dragonflydb-dragonfly.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/dragonflydb-dragonfly","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=dragonflydb-dragonfly","description":"A modern replacement for Redis and Memcached","homepage_url":"https://www.dragonflydb.io/","license":"Other","open_issues":301,"watchers":167,"ai_summary":"DragonflyDB is built in C++ and serves as an advanced cache, key-value store, and message broker with support for vector search.","readme_excerpt":"<p align=\"center\">\n  <a href=\"https://dragonflydb.io\">\n    <img  src=\"/.github/images/logo-full.svg\"\n      width=\"284\" border=\"0\" alt=\"Dragonfly\">\n  </a>\n</p>\n\n \n\n> Before moving on, please consider giving us a GitHub star ⭐️. Thank you!\n\nOther languages:  [简体中文](README.zh-CN.md) [日本語](README.ja-JP.md) [한국어](README.ko-KR.md) [Português](README.pt-BR.md)\n\n[Website](https://www.dragonflydb.io/) • [Docs](https://dragonflydb.io/docs) • [Quick Start](https://www.dragonflydb.io/docs/getting-started) • [Community Discord](https://discord.gg/HsPjXGVH85) • [Dragonfly User Conference](https://www.dragonflydb.io/events/dragonfly-ascent) • [Join the Dragonfly Community](https://www.dragonflydb.io/community)\n\n[GitHub Discussions](https://github.com/dragonflydb/dragonfly/discussions) • [GitHub Issues](https://github.com/dragonflydb/dragonfly/issues) • [Contributing](https://github.com/dragonflydb/dragonfly/blob/main/CONTRIBUTING.md) • [AI Agents Guide](AGENTS.md) • [Dragonfly Cloud](https://www.dragonflydb.io/cloud)\n\n## The world's most efficient in-memory data store\n\nDragonfly is an in-memory data store built for modern application workloads.\n\nFully compatible with Redis and Memcached APIs, Dragonfly requires no code changes to adopt. Compared to legacy in-memory datastores, Dragonfly delivers 25X more throughput, higher cache hit rates with lower tail latency, and can run on up to 80% less resources for the same sized workload.\n\n## Contents\n\n- [Benchmarks](#benchmarks)\n- [Quick start](https://github.com/dragonflydb/dragonfly/tree/main/docs/quick-start)\n- [Configuration](#configuration)\n- [Design decisions](#design-decisions)\n- [Background](#background)\n- [Build from source](./docs/build-from-source.md)\n- [Contributors](#contributors)\n\n## <a name=\"benchmarks\"><a/>Benchmarks\n\nWe first compare Dragonfly with Redis on `m5.large` instance which is commonly used to run Redis\ndue to its single-threaded architecture. The benchmark program runs from another\nload-test instance (c5n) in the same AZ using `memtier_benchmark  -c 20 --test-time 100 -t 4 -d 256 --distinct-client-seed`\n\nDragonfly shows a comparable performance:\n\n1. SETs (`--ratio 1:0`):\n\n|  Redis                                   |      DF                                |\n| -----------------------------------------|----------------------------------------|\n| QPS: 159K, P99.9: 1.16ms, P99: 0.82ms    | QPS:173K, P99.9: 1.26ms, P99: 0.9ms    |\n|                                          |                                        |\n\n2. GETs (`--ratio 0:1`):\n\n|  Redis                                  |      DF                                |\n| ----------------------------------------|----------------------------------------|\n| QPS: 194K, P99.9: 0.8ms, P99: 0.65ms    | QPS: 191K, P99.9: 0.95ms, P99: 0.8ms   |\n\nThe benchmark above shows that the algorithmic layer inside DF that allows it to scale vertically\ndoes not take a large toll when running single-threaded.\n\nHowever, if we take a bit stronger instance (m5.xlarge), the gap between DF and Redis starts growing.\n(`memtier_benchmark  -c 20 --test-time 100 -t 6 -d 256 --distinct-client-seed`):\n1. SETs (`--ratio 1:0`):\n\n|  Redis                                  |      DF                                |\n| ----------------------------------------|----------------------------------------|\n| QPS: 190K, P99.9: 2.45ms, P99: 0.97ms   |  QPS: 279K , P99.9: 1.95ms, P99: 1.48ms|\n\n2. GETs (`--ratio 0:1`):\n\n|  Redis                                  |      DF                                |\n| ----------------------------------------|----------------------------------------|\n| QPS: 220K, P99.9: 0.98ms , P99: 0.8ms   |  QPS: 305K, P99.9: 1.03ms, P99: 0.87ms |\n\n\nDragonfly throughput capacity continues to grow with instance size,\nwhile single-threaded Redis is bottlenecked on CPU and reaches local maxima in terms of performance.\n\n<img src=\"http://static.dragonflydb.io/repo-assets/aws-throughput.svg\" width=\"80%\" border=\"0\"/>\n\nIf we compare Dragonfly and Redis on","github_created_at":"2021-12-11T10:00:42+00:00","created_at":"2026-07-11T11:32:47.952022+00:00","updated_at":"2026-08-23T00:00:57.036713+00:00","categories":[{"slug":"vector-databases","name":"Vector Databases","url":"https://www.graphcanon.com/categories/vector-databases","markdown_url":"https://www.graphcanon.com/categories/vector-databases.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/vector-databases"}],"tags":[{"slug":"cache","name":"cache"},{"slug":"cpp","name":"cpp"},{"slug":"database","name":"database"},{"slug":"fibers","name":"fibers"},{"slug":"in-memory","name":"in-memory"},{"slug":"key-value","name":"key-value"},{"slug":"memcached","name":"memcached"},{"slug":"message-broker","name":"message-broker"}],"trust":{"provenance":{"is_fork":false,"github_id":437245741,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-08-23T00:00:56.211Z","maintenance":{"label":"Very active","score":96,"methodology":"github_public_v1","releases_90d":3,"days_since_push":0,"last_release_at":"2026-08-06T06:54:05Z","stars_delta_30d":115,"open_issues_delta_30d":9},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T11:32:49.117Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-08-23T00:00:56.733Z"},"languages":{"value":["c++","python"],"source":"github.language+pyproject.toml","observed_at":"2026-08-23T00:00:56.733Z"},"license_spdx":{"value":"Other","source":"github.license","observed_at":"2026-08-23T00:00:56.733Z"}},"decision_facts":{"hosting":null,"pricing":{"model":"unknown","summary":"The specific cost structure for using DragonflyDB is not documented in this repository content."},"requirements":{"notes":["DragonflyDB is most effective in environments capable of leveraging multi-threading and low-level optimization features"],"min_ram_gb":4,"requires_docker":false},"constraints":{"min_ram_gb":4,"pricing_model":"unknown","requires_docker":false},"when_to_use":["If your application requires high-performance vector search within a unified platform, DragonflyDB integrates this capability out-of-the-box.","Preferring native C++ implementation can lead to significant performance benefits in scenarios where low-level operations and integration are crucial."],"when_not_to_use":["When a smaller footprint is required due to limited resources or preference for lightweight solutions, older but more established tools like Memcached may be preferable.","If your ecosystem already heavily relies on Redis-specific features that have been built over years of use and customization, DragonflyDB might not offer the same level of compatibility or feature set"],"source":"enrich:decision_facts","observed_at":"2026-07-11T13:01:46.172Z"},"constraint_facets":{"min_ram_gb":4,"pricing_model":"unknown","requires_docker":false},"decision_summary":[{"label":"Pricing","value":"unknown - The specific cost structure for using DragonflyDB is not documented in this repository content."},{"label":"Requirements","value":"Min 4 GB RAM; DragonflyDB is most effective in environments capable of leveraging multi-threading and low-level optimization features"},{"label":"Adopt for","value":"DragonflyDB positions itself as an advanced cache and database solution that competes directly with established tools like Redis and Memcached while introducing key features such as efficient support for vector search."}]}}