Next, let’s add Cipher as an MCP server so agents can discover it automatically • Update "settings.json" if you are using Gemini CLI
• If you’re using Claude Code, add the same config to .mcp.json Now your coding agents can connect to Cipher locally and have long‑term memory
@sumanth_077
-
Add Cipher as MCP Server for Agent Memory
By
–
-
Installing Cipher and Setting Up Your Environment
By
–
First let's install Cipher and set up your environment: • Install globally: npm install -g @byterover/cipher
• Add .env with your provider (we’ll use Ollama for local embeddings, but OpenAI/Gemini also work)
• Create memAgent/cipher.yml to define your model + system prompt -
Cipher: Open-Source Memory Layer for Coding Agents
By
–
We’ll use Cipher, an open‑source memory layer for coding agents. You can run Cipher as an MCP server so coding agents like Claude Code, Gemini CLI, or plugins for VS Code, Cursor, and Windsurf can connect directly and use its memory layer out of the box
-
Building Persistent Memory for Coding Agents Between Sessions
By
–
Coding agents have a major limitation: they forget everything between sessions. Without memory, they can’t retain project context, past fixes, or key decisions. What they need is a persistent memory layer to store and recall context. Let’s see how to set that up.
-
Give Coding Agents Long-Term Memory with One Line
By
–
You can now make Claude Code, Gemini CLI, and other coding agents 10x more powerful by giving them long‑term memory! It just takes a single line of code. Here’s a step‑by‑step breakdown (100% local):
-
Build a GPT-like Large Language Model from Scratch
By
–
Build a Large Language Model from scratch! This repository contains the code for developing, pretraining, and finetuning a GPT-like large language model. 100% Free & Open Source
-
Axolotl: YAML-Based Fine-Tuning Framework with Memory Optimization
By
–
4. Axolotl • Yaml-based setup for fine-tuning, LoRA/QLoRA, DPO, GRPO, and multimodal workflows
• Includes kernel optimizations for memory-efficient training GitHub repo → -
DeepSpeed: Distributed Fine-tuning Framework for Large-Scale LLM Training
By
–
3. DeepSpeed • Built for large-scale distributed fine-tuning with ZeRO and FSDP
• Optimized for multi-GPU and multi-node training with advanced memory management
• Trusted in production environments for scalable LLM training GitHub repo → -
LLaMA Factory: Fine-tune 100+ Models with LoRA and QLoRA
By
–
2. LLaMA Factory • Fine-tune over 100 models (LLaMA, Mistral, Gemma, etc.) using a simple CLI or WebUI
• Supports LoRA, QLoRA, full or frozen fine-tuning across 2–8‑bit precision GitHub repo → -
Unsloth AI: Fine-tune LLMs 2× faster with 70% less VRAM
By
–
1. Unsloth AI • Fine-tune models like Qwen3, Llama 4, and Gemma 3 up to 2× faster with 70% less VRAM
• Supports low-resource setups and runs on consumer GPUs or even Colab/Kaggle with ~3 GB VRAM GitHub repo →