技能潮 SkillTide 提交收录
官方说明3 个来源MCP 服务3 天前
dakera-ai/dakera-mcp

dakera-ai/dakera-mcp

🦀 🏠 🍎 🪟 🐧 - Self-hosted MCP-native agent memory server
在 GitHub 查看 ↗直链 · 无中转页
官方说明🦀 🏠 🍎 🪟 🐧 - Self-hosted MCP-native agent memory server. 83 tools for persistent, decay-weighted episodic memory across sessions. RocksDB + HNSW, 87.8% LoCoMo benchmark. Docker Compose deployment, mult
来源明细
收录自 rohitg00/awesome-devops-mcp-servers 榜单(我们从中收集的条目之一) · 条目类型:MCP 服务
收录与活跃
收录于 2026-10-14 · 最近见到 2026-10-16 · 共见到 4 次 · 被 3 个来源列出
评分构成
综合分 303 · 3 个来源 · mcp
常见问题(答案都来自我们的记录)
怎么安装?
我们【没有】从该仓库取到安装命令(我们的 install 覆盖率只有约 4%)。请看它的 README 或 releases 页。
它适合谁 / 用来做什么?
我们把它归在这些标签下: MCP 服务。标签来自条目自身,不是我们强加的分类。
谁维护它、还在更新吗?
我们收录于 2026-10-14;最近见到 2026-10-16。这里没有"官方认证"或"质量评级"——我们只记录来源与时间。
第三方质量标记

⚡ dakera-mcp

以下摘录自该仓库的 README(片段) · 在 GitHub 读完整 README →

MCP server for Dakera AI. Gives any MCP-compatible AI agent persistent, queryable memory — with smart token management built in.
Works with Claude, Claude Code, and any MCP-compatible framework.
Part of Dakera AI — the memory engine for AI agents.
> The Dakera memory engine scores **88.2% Recall@20 on LoCoMo** (1,536 evaluated questions · LLM-judged retrieval recall) — benchmark details
---
Architecture: 14 core tools + on-demand discovery
Starting every agent session with 60+ tool schemas wastes ~15K tokens before you write a single message. dakera-mcp solves this with **hybrid tool exposure**:
- **14 tools loaded by default** — the 12 highest-frequency memory operations + 2 meta-discovery tools
- **On-demand expansion** — use dakera_discover_tools and dakera_load_tools to fetch additional tool schemas only when you need them
Default tool set (core profile)
| Tool | Purpose |
|---|---|
| dakera_store | Store a memory with importance, tags, and type |
| dakera_recall | Semantic recall by query text |
| dakera_search | Advanced memory search with tag/type filters |
| dakera_session_start | Start a session to group related memories |
| dakera_session_end | End a session with optional summary |
| dakera_batch_recall | Bulk filter-based recall (by tags, importance, time) |
| dakera_forget | Delete specific memories by ID |
| dakera_hybrid_search | Combined vector + BM25 search |
| dakera_fulltext_search | BM25 full-text search |
| dakera_knowledge_graph | Build a knowledge graph from a seed memory |
| dakera_extract | Extract entities and structure from free-form text |
| dakera_batch_forget | Bulk delete by tags, type, or time range |
| dakera_discover_tools | Search the full tool catalog by keyword or tier |
| dakera_load_tools | Load full schemas for specific tools on demand |
Profiles & token cost
| Profile | Tools | ~Tokens | How to enable |
|---|---|---|---|
| **core** | 14 | ~3,400 | Default — always loaded |
| **admin** | 34 | ~6,750 | DAKERA_MCP_PROFILE=admin |
| **power** | 82 | ~17,250 | DAKERA_MCP_PROFILE=power |
| **all** | 102 | ~20,600 | DAKERA_MCP_PROFILE=all |
Token figures are estimates (JSON bytes / 3). The attachment tools below count in power and all,
but only appear while the connected server has the feature on (see Dakera v0.12).
Accessing additional tools
Profile selection
The profile controls which tools appear in tools/list. Three ways to set it:
**1. Per-request** (in tools/list params):
**2. Environment variable** (applies to all requests):
**3. Default**: core (14 tools, ~3,400 tokens)
---
Dakera v0.12
dakera-mcp 0.12.2 works against **Dakera v0.11.108 and v0.12.0 – v0.12.2** servers. Every tool keeps
its name and arguments; the additions are optional arguments that are sent only when you supply them
(or that an older server ignores), and tools that call new routes and say so on a server without them.
| Dakera server | dakera-mcp 0.12.2 |
|---|---|
| v0.12.2 | every tool; the attachment tools while DAKERA_ATTACHMENTS (and DAKERA_VISION for images) is on |
| v0.12.0, v0.12.1 | every tool; dakera_session_touch and dakera_agent_create answer that nothing is needed (sessions are not ended for inactivity there, and an agent is created by its first memory); dakera_whoami says it needs v0.12.2; listings return full content (no preview) and include derived sentence sub-memories |
| v0.11.108 | as v0.12.0, and the attachment tools, dakera_encryption_status and dakera_embed_migration_status are not listed (a direct call says they need v0.12); dakera_encryption_rotate_key needs new_key |
| older | not tested |
New with Dakera v0.12.2
| Tool / argument | Tier | What it does |
|---|---|---|
| dakera_session_start idle_timeout_secs | core | the server ends a session idle for 4 h by default; this sets the session's own timeout (0 = never, at most 30 days) |
来源
awesome · https://github.com/dakera-ai/dakera-mcp
按领域浏览
MCP 服务
收录于
昨天

更多MCP 服务

查看MCP 服务全部 5,525 条 →

所属领域与标签

每个标签都能点进去看同类的全部条目。数字是当前库里的真实条数。

浏览全部领域 →

← 返回索引