agent-memory-kit: Replacing mem9 with Markdown and Git
Nov 17, 2026 · 16 min read · Agent Memory agent-memory-kit mem9 Claude Code Codex Kiro Git Markdown MCP Open Source AWS Lambda Amazon S3 ·
A few months ago, I wrote about self-hosting mem9 on AWS so the agents I use could share memory. I have now replaced that workflow with agent-memory-kit, a new project I have released under the MIT license. The workstation side keeps memory as Markdown notes in a private Git repository. Each machine has a clone. Claude …
Read More about agent-memory-kit: Replacing mem9 with Markdown and Git
Start a Codex task in a remote SSH terminal, then check progress and send the next instruction from your phone. The key is connecting both clients to the same running session. My phone already had an SSH connection to the remote host through ChatGPT's Codex interface. This fix lets it follow tasks started from the CLI. …
Read More about Share a Codex Session Between ChatGPT Mobile and SSH
When Codex uses Bedrock's OpenAI-compatible API, switching models can break requests: the selected model changes, but the provider still points to the same AWS Region. The failure appears both when using Codex directly and when operating it through the ChatGPT app. In both cases, Codex makes the model API request. A …
Read More about Switch Bedrock Models in Codex and the ChatGPT AppGemini Transcribe vs FunASR: Production Economics
Sep 7, 2026 · 13 min read · Gemini 3.5 Transcribe FunASR Speech to Text Amazon ECS GPU Spot Podcast Transcription FinOps Speaker Diarization ·
- The Three-Phase Transcription Pipeline A production podcast transcript is not produced by one model call. The pipeline behind these measurements has three stages: Phase 1: VAD, speech recognition, punctuation, timestamps, and speaker diarization. Phase 2: speaker identity verification and label correction. Phase 3: …
Read More about Gemini Transcribe vs FunASR: Production EconomicsClose Your Laptop: Claude Code on Bedrock AgentCore
Jul 10, 2026 · 16 min read · AWS Claude Code Amazon Bedrock AgentCore SST Pulumi Firecracker DevSecOps ·
If you have ever set an AI coding agent like Claude Code loose on a large code modification task, you know the anxiety. The task will run for 45 minutes, recursive calls will compile code, search tests, and fix bugs. You are locked to your machine. If your Wi-Fi drops for a second, your laptop battery dies, or you …
Read More about Close Your Laptop: Claude Code on Bedrock AgentCoreMCP OAuth on AgentCore Gateway + Cognito via APIGW Façade
May 19, 2026 · 18 min read · MCP Model Context Protocol AWS Bedrock AgentCore AgentCore Gateway Amazon Cognito API Gateway SST OAuth 2.1 RFC 9728 RFC 8414 RFC 7591 PKCE Claude Code ·
Introduction Amazon Bedrock AgentCore Gateway is the most pragmatic way to host a Model Context Protocol server on AWS today. Declare your tools as OpenAPI or as Lambda targets, get a managed multi-target MCP endpoint, and inherit AWS-native authentication via a customJwtAuthorizer. For machine-to-machine traffic that …
Read More about MCP OAuth on AgentCore Gateway + Cognito via APIGW FaçadeAgent Toolkit for AWS: What It Changes for Claude Code
May 12, 2026 · 12 min read · AWS Claude Code MCP Agent Toolkit Amazon Bedrock CloudFormation IAM Serverless ·
If you've been using Claude Code for AWS development, you've probably seen the pattern: you paste a CloudFormation snippet into your session, Claude suggests something plausible, you deploy it, and the stack events stream lights up with CREATE_FAILED on a property the model couldn't have known about — because its …
Read More about Agent Toolkit for AWS: What It Changes for Claude CodeTrack Claude Code Cost Per Project with Bedrock Tagging
Apr 29, 2026 · 9 min read · AWS Amazon Bedrock Claude Code Cost Management IAM Session Tags Cost Allocation FinOps ·
If you run claude against Amazon Bedrock across a dozen repos, your bill arrives as one opaque number. Until recently, the workaround was clunky — create an application inference profile per project, swap them by hand, hope you remembered which one was active. In April 2026, AWS shipped native per-principal cost …
Read More about Track Claude Code Cost Per Project with Bedrock TaggingOwn Your Agents' Memory: Self-Hosted mem9 on AWS

Introduction Every agent session starts amnesic. You explain your deployment topology to Claude Code on Monday, and on Tuesday Codex asks the same question. You tell one agent that Aurora MySQL cannot run your vector workload, and the next agent cheerfully proposes it. The knowledge that actually compounds — decisions …
Read More about Own Your Agents' Memory: Self-Hosted mem9 on AWSMulti-Tenant Bedrock Agents Security with Cedar
Jun 6, 2026 · 12 min read · AWS Bedrock Agents AgentCore Cedar Amazon Verified Permissions Multi-Tenant Zero Trust SaaS Security ·
TL;DR (30-Second Read) With Amazon Bedrock AgentCore now generally available — including AgentCore Identity for agent authentication and AgentCore Policy, which enforces Cedar rules by intercepting every tool call before execution — the security design for multi-tenant SaaS on Bedrock Agents has reached an inflection …
Read More about Multi-Tenant Bedrock Agents Security with Cedar