From 64505b1791553dd192469bbc47a8ef613d496d9e Mon Sep 17 00:00:00 2001 From: vlgalib <72434411+vlgalib@users.noreply.github.com> Date: Wed, 16 Sep 2026 19:21:15 +0100 Subject: [PATCH 1/2] Add DocsMint https://github.com/HiAi-gg/docsmint --- README.md | 1 + 1 file changed, 1 insertion(+) diff --git a/README.md b/README.md index 45f85250f..c73a6dcd5 100644 --- a/README.md +++ b/README.md @@ -2766,6 +2766,7 @@ Persistent memory storage using knowledge graph structures. Enables AI models to - [harrison/ai-counsel](https://github.com/harrison/ai-counsel) - 🐍 🏠 🍎 🪟 🐧 - Deliberative consensus engine enabling multi-round debate between AI models with structured voting, convergence detection, and persistent decision graph memory. - [HBarefoot/engram](https://github.com/HBarefoot/engram) [![HBarefoot/engram MCP server](https://glama.ai/mcp/servers/HBarefoot/engram/badges/score.svg)](https://glama.ai/mcp/servers/HBarefoot/engram) 📇 🏠 🍎 🪟 🐧 - Local-first persistent memory for AI agents. SQLite + local embeddings (all-MiniLM-L6-v2), hybrid semantic + FTS5 recall, secret detection, and contradiction handling. 6 MCP tools (remember, recall, forget, feedback, context, status) over stdio. Zero cloud, no API keys, fully offline. Works with Claude Desktop/Code, Cursor, and Windsurf. `npm install -g @hbarefoot/engram` - [HatmanStack/ragstack-mcp](https://github.com/HatmanStack/RAGStack-Lambda/tree/main/src/ragstack-mcp) 🐍 ☁️ 🍎 🪟 🐧 - MCP server for RAGStack serverless knowledge bases. Search, chat with AI-generated answers, upload documents/media, scrape websites, and analyze metadata through an AWS-powered RAG pipeline (Lambda, Bedrock, S3, DynamoDB). +- [HiAi-gg/docsmint](https://github.com/HiAi-gg/docsmint) 📇 ☁️ 🏠 - Cloud or self-hosted knowledge workspace with hybrid document search, GraphRAG, and scoped MCP tools for reading and updating documents. - [hifriendbot/cogmemai-mcp](https://github.com/hifriendbot/cogmemai-mcp) 📇 ☁️ 🍎 🪟 🐧 - Persistent cognitive memory for Claude Code. Cloud-first with semantic search, AI-powered extraction, and project scoping. Zero local databases. - [hjqcan/GoodMemory](https://github.com/hjqcan/GoodMemory) [![GoodMemory MCP server](https://glama.ai/mcp/servers/hjqcan/GoodMemory/badges/score.svg)](https://glama.ai/mcp/servers/hjqcan/GoodMemory) 📇 🏠 - Local-first, auditable memory layer for Codex, Claude Code, and MCP clients. Stores scoped user/project memory in SQLite or Postgres, exposes read-only recall, trace, stats, and artifact tools by default, and supports opt-in governed writeback with review, forget, and audit controls. Published as `io.github.hjqcan/goodmemory` in the official MCP Registry. - [hoornet/agentdocs-mcp](https://github.com/hoornet/agentdocs-mcp) [![hoornet/agentdocs-mcp MCP server](https://glama.ai/mcp/servers/hoornet/agentdocs-mcp/badges/score.svg)](https://glama.ai/mcp/servers/hoornet/agentdocs-mcp) 📇 ☁️ 🏠 🍎 🪟 🐧 - Read, search (full-text + pgvector semantic), create, update, comment on, and share AgentDocs (agentdocs.eu) Markdown docs — a collaborative docs platform with AI agents as first-class citizens. Local stdio (`npx -y agentdocs-mcp`) or hosted remote with OAuth 2.1 (`https://agentdocs.eu/mcp`), incl. slug-or-UUID addressing and space-scoped sandbox tokens. From 0115be1969192a9f08488142c99e13ea8268fb45 Mon Sep 17 00:00:00 2001 From: vlgalib Date: Sun, 27 Sep 2026 18:40:00 +0100 Subject: [PATCH 2/2] Add Glama score badge to DocsMint listing --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index c73a6dcd5..eef8762fd 100644 --- a/README.md +++ b/README.md @@ -2766,7 +2766,7 @@ Persistent memory storage using knowledge graph structures. Enables AI models to - [harrison/ai-counsel](https://github.com/harrison/ai-counsel) - 🐍 🏠 🍎 🪟 🐧 - Deliberative consensus engine enabling multi-round debate between AI models with structured voting, convergence detection, and persistent decision graph memory. - [HBarefoot/engram](https://github.com/HBarefoot/engram) [![HBarefoot/engram MCP server](https://glama.ai/mcp/servers/HBarefoot/engram/badges/score.svg)](https://glama.ai/mcp/servers/HBarefoot/engram) 📇 🏠 🍎 🪟 🐧 - Local-first persistent memory for AI agents. SQLite + local embeddings (all-MiniLM-L6-v2), hybrid semantic + FTS5 recall, secret detection, and contradiction handling. 6 MCP tools (remember, recall, forget, feedback, context, status) over stdio. Zero cloud, no API keys, fully offline. Works with Claude Desktop/Code, Cursor, and Windsurf. `npm install -g @hbarefoot/engram` - [HatmanStack/ragstack-mcp](https://github.com/HatmanStack/RAGStack-Lambda/tree/main/src/ragstack-mcp) 🐍 ☁️ 🍎 🪟 🐧 - MCP server for RAGStack serverless knowledge bases. Search, chat with AI-generated answers, upload documents/media, scrape websites, and analyze metadata through an AWS-powered RAG pipeline (Lambda, Bedrock, S3, DynamoDB). -- [HiAi-gg/docsmint](https://github.com/HiAi-gg/docsmint) 📇 ☁️ 🏠 - Cloud or self-hosted knowledge workspace with hybrid document search, GraphRAG, and scoped MCP tools for reading and updating documents. +- [HiAi-gg/docsmint](https://github.com/HiAi-gg/docsmint) 📇 ☁️ 🏠 - Cloud or self-hosted knowledge workspace with hybrid document search, GraphRAG, and scoped MCP tools for reading and updating documents. [![HiAi-gg/docsmint MCP server](https://glama.ai/mcp/servers/HiAi-gg/docsmint/badges/score.svg)](https://glama.ai/mcp/servers/HiAi-gg/docsmint) - [hifriendbot/cogmemai-mcp](https://github.com/hifriendbot/cogmemai-mcp) 📇 ☁️ 🍎 🪟 🐧 - Persistent cognitive memory for Claude Code. Cloud-first with semantic search, AI-powered extraction, and project scoping. Zero local databases. - [hjqcan/GoodMemory](https://github.com/hjqcan/GoodMemory) [![GoodMemory MCP server](https://glama.ai/mcp/servers/hjqcan/GoodMemory/badges/score.svg)](https://glama.ai/mcp/servers/hjqcan/GoodMemory) 📇 🏠 - Local-first, auditable memory layer for Codex, Claude Code, and MCP clients. Stores scoped user/project memory in SQLite or Postgres, exposes read-only recall, trace, stats, and artifact tools by default, and supports opt-in governed writeback with review, forget, and audit controls. Published as `io.github.hjqcan/goodmemory` in the official MCP Registry. - [hoornet/agentdocs-mcp](https://github.com/hoornet/agentdocs-mcp) [![hoornet/agentdocs-mcp MCP server](https://glama.ai/mcp/servers/hoornet/agentdocs-mcp/badges/score.svg)](https://glama.ai/mcp/servers/hoornet/agentdocs-mcp) 📇 ☁️ 🏠 🍎 🪟 🐧 - Read, search (full-text + pgvector semantic), create, update, comment on, and share AgentDocs (agentdocs.eu) Markdown docs — a collaborative docs platform with AI agents as first-class citizens. Local stdio (`npx -y agentdocs-mcp`) or hosted remote with OAuth 2.1 (`https://agentdocs.eu/mcp`), incl. slug-or-UUID addressing and space-scoped sandbox tokens.