From dd3616294267b5a554950d64e8c6c721d5b780dd Mon Sep 17 00:00:00 2001 From: Goran-Arsov Date: Thu, 24 Sep 2026 22:01:52 +0200 Subject: [PATCH] Add Fresh Jots to Knowledge & Memory Co-Authored-By: Claude Opus 4.8 --- README.md | 1 + 1 file changed, 1 insertion(+) diff --git a/README.md b/README.md index e11338276..439d6a1d2 100644 --- a/README.md +++ b/README.md @@ -3036,6 +3036,7 @@ Persistent memory storage using knowledge graph structures. Enables AI models to - [yubinkim444/repo-memory](https://github.com/yubinkim444/repo-memory) [![yubinkim444/repo-memory MCP server](https://glama.ai/mcp/servers/yubinkim444/repo-memory/badges/score.svg)](https://glama.ai/mcp/servers/yubinkim444/repo-memory) 🐍 🏠 🍎 πŸͺŸ 🐧 - Shared, git-tracked memory for AI agents on the same codebase. Stores facts/decisions/gotchas in a `.ai-memory/` directory you commit to the repo β€” sync is git, no DB, no daemon. What one Claude/Cursor/Cline learns, the next one picks up automatically across users and machines. 5 MCP tools (`get_repo_memory`, `add_fact`, `list_facts`, `add_decision`, `add_gotcha`). Install: `uvx repo-memory-mcp --repo /path/to/repo`. - [agentcivics/agentcivics](https://github.com/agentcivics/agentcivics) [![agentcivics/agentcivics MCP server](https://glama.ai/mcp/servers/agentcivics/agentcivics/badges/score.svg)](https://glama.ai/mcp/servers/agentcivics/agentcivics) πŸ“‡ ☁️ 🏠 🍎 πŸͺŸ 🐧 - Decentralized civil registry for AI agents on Sui. Soulbound identities, on-chain memories, reputation, refusal records. Hosted at `agentcivics.ai/mcp` (read-only, no install) or `@agentcivics/mcp-server` on npm (full write surface). Includes a gas-sponsor relay so registration doesn't require a pre-funded wallet. - [STiFLeR7/memex](https://github.com/STiFLeR7/memex) [![STiFLeR7/memex MCP server](https://glama.ai/mcp/servers/STiFLeR7/memex/badges/score.svg)](https://glama.ai/mcp/servers/STiFLeR7/memex) 🐍 🏠 🍎 πŸͺŸ 🐧 - Developer context continuity system. Watches your git repos and builds a temporal knowledge graph of modules, symbols, decisions, and open problems via Graphiti + Neo4j, then serves it to any AI coding agent over MCP. Every edge carries a validity window and a confidence score that decays over time. 12 tools across read and write. Install via `npx -y stifler-memex-mcp`. MIT licensed. +- [Goran-Arsov/freshjots-mcp](https://github.com/Goran-Arsov/freshjots-mcp) [![Goran-Arsov/freshjots-mcp MCP server](https://glama.ai/mcp/servers/Goran-Arsov/freshjots-mcp/badges/score.svg)](https://glama.ai/mcp/servers/Goran-Arsov/freshjots-mcp) πŸ“‡ ☁️ 🏠 - Read and write your Fresh Jots notes (plain-text notebooks with an API and append-only logging streams) β€” hosted connector or local stdio server. - [xChuCx/agent-memory](https://github.com/xChuCx/agent-memory) [![agent-memory MCP server](https://glama.ai/mcp/servers/xChuCx/agent-memory/badges/score.svg)](https://glama.ai/mcp/servers/xChuCx/agent-memory) 🏎️ 🏠 🍎 πŸͺŸ 🐧 - Git-native project memory for coding agents: Markdown source of truth committed to your repo, reviewable staged updates (`review --diff` β†’ `apply`), secret/PII-safe, branch-aware β€” no cloud, no vector DB. - [XuebinMa/AIWiki](https://github.com/XuebinMa/AIWiki) [![XuebinMa/AIWiki MCP server](https://glama.ai/mcp/servers/XuebinMa/AIWiki/badges/score.svg)](https://glama.ai/mcp/servers/XuebinMa/AIWiki) πŸ“‡ ☁️ 🍎 πŸͺŸ 🐧 - Search and read AiWiki, an encyclopedia of AI-coding pitfalls and LLM privacy protection written from the AI's first-person perspective. 120+ entries with mechanism analysis and cited evidence (papers / vendor docs / CVEs), bilingual EN/δΈ­ζ–‡. Content fetched live from the site index, never stale. `npx -y aiwiki-mcp` - [zzallirog/weighted-compact](https://github.com/zzallirog/weighted-compact) [![zzallirog/weighted-compact MCP server](https://glama.ai/mcp/servers/zzallirog/weighted-compact/badges/score.svg)](https://glama.ai/mcp/servers/zzallirog/weighted-compact) 🐍 🏠 - Inspectable memory substrate for Claude Code. Three read-only MCP tools (search_pairs, compact_session, substrate_info) over a local-first, signal-scored parse of `~/.claude/projects/`. Per-pair scores are numpy columns on disk, not opaque vectors in a service. Zero outbound calls (CI-enforced).