Tagged: agents
18 posts from the Dosu blog
Turning Coding Sessions Into Shared Agent Memory
Recurring discoveries in Claude Code and Codex show why shared agent memory needs explanations and sources.
Taylor DolezalHead of OSSHow 20 Vercel AI SDK tickets drove the agent cost gap
Claude Code on Opus 5.5 and Codex on GPT 6.1 Sol attempted the same 49 tickets. The recorded cost gap came entirely from high-scope work.
Taylor DolezalHead of OSSProcedural Memory for Coding Agents: Turning Knowledge Into Action
Learn how to turn a coding agent's discovery into a shared procedure, choose where the instructions belong, and check that the next agent uses them correctly.
Taylor DolezalHead of OSSSemantic memory for coding agents needs a history
Your coding agent needs to know which facts still apply. Our Celery-to-DBOS migration shows why semantic memory needs scope, dates, and source evidence.
Taylor DolezalHead of OSSEpisodic memory for coding agents: What survives your sessions
Episodic memory is a coding agent's record of past sessions. Saved lessons can outlive the transcripts behind them, so keep each lesson tied to its source.
Taylor DolezalHead of OSSHow to Build Agent Memory: Maintenance
How to keep agent memory useful as things change: preserve evidence, scope updates, choose maintenance triggers, and measure whether memories still help.
Devin SteinFounder and CEOHow to Build Agent Memory: Search & Retrieval
How agents find and use what they've learned: choosing a search strategy, returning useful context, and balancing precise evidence with higher-level understanding.
Devin SteinFounder and CEOHow to Build Agent Memory: Knowledge Capture
How to decide what agents should remember: five questions for evaluating knowledge, choosing its structure, and capturing discoveries for future work.
Devin SteinFounder and CEOHow to design a CLI login flow for coding agents
Design a CLI login for coding agents with a ticket flow that pauses, resumes in a new process, and returns the next command in JSON. Learn how Dosu built it.
Taylor DolezalHead of OSSHow to Build Agent Memory: Where Does Knowledge Live?
Agent memory starts with representation and storage. Here's how to decide what knowledge looks like, where it lives, and what is worth maintaining.
Devin SteinFounder and CEOYour coding agent budget pays for context, not code
Planning and gathering context account for two thirds of agent costs.
OSS has Changed. So has Dosu.
Changes coming to Dosu OSS plan on Sept 1st. ~96% of OSS projects see no change.
Devin SteinFounder and CEOHow to Build Agent Memory: The Building Blocks of Agent Memory
We break down 'Are We Ready for an Agent-Native Memory System?' — the four building blocks of agent memory: storage, extraction, retrieval, and maintenance.
Devin SteinFounder and CEOA stale AGENTS.md is worse than no AGENTS.md
Cloudflare built an internal platform to keep AGENTS.md files fresh across thousands of repos. Here are the methods to keep yours current, and how we do it at Dosu.
Taylor DolezalHead of OSSAgentic Infrastructure: What We Learned Hosting a Panel With LanceDB, CodeRabbit, and CrewAI
Four companies focused on agentifying their tech stack. One rewrote its codebase for AI. Another found PII leaking through OpenTelemetry traces.
Why Your Coding Agent Needs More Than a Static README
Vercel proved static context beats on-demand skills for coding agents. But static docs have limits, so we extended that principle with a living knowledge base and the Dosu MCP.
George XuFounding BizOps LeadWhat tldraw and goose Are Teaching Us About AI-Ready Open Source
Two open source projects face the same AI contribution crisis and make different choices. Both were right.
Taylor DolezalHead of OSSThe Code Understanding Paradox: When AI Makes Writing Code Fast but Understanding It Slow
I've been thinking about Sonar CEO Tariq Shaukat's recent blog post Solving the Engineering Productivity Paradox from a Dosu angle.
Devin SteinFounder and CEO