[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-860":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":10,"totalLinesOfCode":10,"stars":12,"forks":13,"watchers":14,"openIssues":15,"contributorsCount":16,"subscribersCount":16,"size":16,"stars1d":17,"stars7d":18,"stars30d":19,"stars90d":16,"forks30d":16,"starsTrendScore":20,"compositeScore":21,"rankGlobal":10,"rankLanguage":10,"license":22,"archived":23,"fork":23,"defaultBranch":24,"hasWiki":25,"hasPages":25,"topics":26,"createdAt":10,"pushedAt":10,"updatedAt":31,"readmeContent":32,"aiSummary":33,"trendingCount":16,"starSnapshotCount":16,"syncStatus":17,"lastSyncTime":34,"discoverSource":35},860,"stash","alash3al\u002Fstash","alash3al","Stash — persistent memory layer for AI agents. Episodes, facts, and working context stored in Postgres. MCP server included. Self-hosted, single binary, no cloud required.","https:\u002F\u002Falash3al.github.io\u002Fstash\u002F",null,"Go",712,35,3,1,0,2,5,25,6,8.67,"Apache License 2.0",false,"main",true,[27,28,29,30],"ai","ai-agents","ai-memory","memory","2026-06-12 02:00:19","# Stash\n\n**Your AI has amnesia. We fixed it.**\n\nEvery LLM starts every conversation from zero. Stash gives your agent persistent memory — it remembers, recalls, consolidates, and learns across sessions. No more explaining yourself from scratch.\n\nOpen source. Self-hosted. Works with any MCP-compatible agent.\n\n## Quick Start\n\n```bash\ngit clone https:\u002F\u002Fgithub.com\u002Falash3al\u002Fstash.git\ncd stash\ncp .env.example .env   # edit with your API key + model\ndocker compose up\n```\n\nThat's it. Postgres + pgvector, migrations, MCP server with background consolidation — all in one command.\n\n## MCP Client Setup\n\nAfter `docker compose up`, Stash exposes an MCP server over SSE at:\n\n```\nhttp:\u002F\u002Flocalhost:8080\u002Fsse\n```\n\nPoint any MCP-compatible client at that URL. Example configs:\n\n**Cursor** — `~\u002F.cursor\u002Fmcp.json`\n```json\n{\n  \"mcpServers\": {\n    \"stash\": {\n      \"url\": \"http:\u002F\u002Flocalhost:8080\u002Fsse\"\n    }\n  }\n}\n```\n\n**Claude Desktop** — `claude_desktop_config.json`\n```json\n{\n  \"mcpServers\": {\n    \"stash\": {\n      \"url\": \"http:\u002F\u002Flocalhost:8080\u002Fsse\"\n    }\n  }\n}\n```\n\n**OpenCode** — `~\u002F.config\u002Fopencode\u002Fconfig.json`\n```json\n{\n  \"mcp\": {\n    \"stash\": {\n      \"type\": \"remote\",\n      \"url\": \"http:\u002F\u002Flocalhost:8080\u002Fsse\",\n      \"enabled\": true\n    }\n  }\n}\n```\n\n**Windsurf** — `~\u002F.codeium\u002Fwindsurf\u002Fmcp_config.json`\n```json\n{\n  \"mcpServers\": {\n    \"stash\": {\n      \"url\": \"http:\u002F\u002Flocalhost:8080\u002Fsse\"\n    }\n  }\n}\n```\n\nWorks with any agent that supports MCP over SSE — Claude Desktop, Cursor, Windsurf, Cline, Continue, OpenAI Agents, Ollama, OpenRouter, and more.\n\n## What It Does\n\nStash is a cognitive layer between your AI agent and the world. Episodes become facts. Facts become relationships. Relationships become patterns. Patterns become wisdom.\n\nAn 8-stage consolidation pipeline turns raw observations into structured knowledge — facts, relationships, causal links, goal tracking, failure patterns, hypothesis verification, and confidence decay. Each stage only processes new data since the last run.\n\n## Learn More\n\n**[alash3al.github.io\u002Fstash →](https:\u002F\u002Falash3al.github.io\u002Fstash\u002F)**\n\n## License\n\nApache 2.0\n","Stash 是一个为AI代理提供持久化记忆层的工具，它将对话、事实和工作上下文存储在Postgres数据库中。该项目采用Go语言编写，具备自托管特性，无需云服务支持，并且包含了一个MCP服务器。其核心功能包括通过8阶段整合管道将原始观察数据转化为结构化的知识体系，涵盖事实关系、因果链、目标追踪等多个方面。Stash适用于任何需要长期记忆能力以改善用户体验的AI应用场合，如聊天机器人、个人助理等，尤其适合那些已经支持MCP协议的客户端使用。","2026-06-11 02:39:50","CREATED_QUERY"]