Self-evolving Context Database for AI Agents. Unify Agent Memory, Knowledge RAG and Skills.
Python agent-contextagent-memoryagent-pluginsagentic-ragcontext-databasedsh-pluginknowledge-basememorymemory-managementself-evolvingvector-database
docs: note benchmark model configuration (#4183)
chenjw9a0f54b300d7
diff --git a/README.md b/README.mdindex 405ee268d..4d52d14ec 100644--- a/README.md+++ b/README.md@@ -94,6 +94,8 @@ viking://resources/my_project/OpenViking 0.3.22 has been evaluated on long-conversation user memory (LoCoMo) and multi-turn agent tasks (tau2-bench). Full results and setup details, including knowledge-base QA, are in the [benchmark report](https://blog.openviking.ai/post/openviking-benchmark-results/); reproduction scripts live in [./benchmark](./benchmark).+The memory evaluation used [Doubao 2.0 Pro](https://console.volcengine.com/ark/region:cn-beijing/model/detail?Id=doubao-seed-2-0-pro) as the VLM and [Doubao-embedding-vision-251215](https://console.volcengine.com/ark/region:cn-beijing/model/detail?Id=doubao-embedding-vision) as the embedding model.+<picture><source media="(prefers-color-scheme: dark)" srcset="docs/images/benchmark-dark.svg"><img alt="Benchmark results. LoCoMo accuracy: OpenClaw 24.20% native vs 82.08% with OpenViking; Hermes 33.38% vs 82.86%; Claude Code 57.21% vs 80.32%. tau2-bench task success: Retail 70.94% vs 77.81%; Airline 54.38% vs 66.25%." src="docs/images/benchmark-light.svg">diff --git a/README_CN.md b/README_CN.mdindex abc19a7a3..bc2d565bc 100644--- a/README_CN.md+++ b/README_CN.md@@ -94,6 +94,8 @@ viking://resources/my_project/OpenViking 0.3.22 的评测覆盖长对话用户记忆(LoCoMo)和多轮智能体任务(tau2-bench)。完整结果和实验设置(含知识库问答)见[评测报告](https://blog.openviking.ai/post/openviking-benchmark-results/),复现脚本在 [./benchmark](./benchmark)。+记忆评测使用 [Doubao 2.0 Pro](https://console.volcengine.com/ark/region:cn-beijing/model/detail?Id=doubao-seed-2-0-pro) 作为 VLM,使用 [Doubao-embedding-vision-251215](https://console.volcengine.com/ark/region:cn-beijing/model/detail?Id=doubao-embedding-vision) 作为 Embedding 模型。+<picture><source media="(prefers-color-scheme: dark)" srcset="docs/images/benchmark-dark.svg"><img alt="Benchmark results. LoCoMo accuracy: OpenClaw 24.20% native vs 82.08% with OpenViking; Hermes 33.38% vs 82.86%; Claude Code 57.21% vs 80.32%. tau2-bench task success: Retail 70.94% vs 77.81%; Airline 54.38% vs 66.25%." src="docs/images/benchmark-light.svg">diff --git a/README_JA.md b/README_JA.mdindex 7bf9c7ff2..5c3aa4428 100644--- a/README_JA.md+++ b/README_JA.md@@ -94,6 +94,8 @@ viking://resources/my_project/OpenViking 0.3.22 は、長い会話でのユーザーメモリ(LoCoMo)と複数ターンのエージェントタスク(tau2-bench)で評価されています。ナレッジベースQAを含む完全な結果と実験設定は[ベンチマークレポート](https://blog.openviking.ai/post/openviking-benchmark-results/)を、再現用スクリプトは [./benchmark](./benchmark) を参照してください。+メモリ評価では、VLM に [Doubao 2.0 Pro](https://console.volcengine.com/ark/region:cn-beijing/model/detail?Id=doubao-seed-2-0-pro)、Embedding モデルに [Doubao-embedding-vision-251215](https://console.volcengine.com/ark/region:cn-beijing/model/detail?Id=doubao-embedding-vision) を使用しました。+<picture><source media="(prefers-color-scheme: dark)" srcset="docs/images/benchmark-dark.svg"><img alt="Benchmark results. LoCoMo accuracy: OpenClaw 24.20% native vs 82.08% with OpenViking; Hermes 33.38% vs 82.86%; Claude Code 57.21% vs 80.32%. tau2-bench task success: Retail 70.94% vs 77.81%; Airline 54.38% vs 66.25%." src="docs/images/benchmark-light.svg">