memcode · terminal
Your agent should know your repo.
Memcode remembers your codebase the way a senior engineer does, then puts a coding agent on top of that memory, right in your terminal. Install in one line.
Prefer to inspect first? Read the install script · Fully open source
Why Memcode
Not another chat wrapper. A persistent memory system that makes the agent actually useful, because it knows what came before.
Knows your repo, not just your files
Memcode builds a living picture of your codebase: how it fits together, what was decided, and why. Every session starts already oriented instead of re-reading everything.
Never starts from zero
Other agents burn the first ten minutes rediscovering your codebase and still miss the why. Memcode picks up exactly where it left off, without spending your tokens to re-learn.
Lives in your terminal
A fast TUI in a single static binary. No Electron, no browser tab, no IDE plugin. It starts instantly and stays out of your way.
Memory that compounds
Context and decisions persist across sessions. The agent gets sharper the longer it works in your repo, because it remembers what it learned last time.
The first session is the last cold start.
Every other agent starts from scratch each session, re-reading files and re-asking questions you already answered. Memcode remembers, and it compounds.
Work like you always do
Commit, edit, ship. No annotations and no special workflow. Memcode watches your repo and keeps up on its own.
It remembers what matters
Not just the code, but the decisions, the dead ends, and the reasons. The context you would otherwise re-explain every session.
Every session starts ahead
Open the terminal and the agent already knows where things stand. No warm-up, no re-reading, no "let me look around first."
Chat, wired to your knowledge
Every frontier model in one place, with your DataHub docs on tap. Ask a question, get an answer grounded in your team's documents, and share the thread.
Recent
Here is what your docs say.
The policy
- Annual plans get a full refund inside the first 30 days, no questions asked
- After 30 days, refunds are prorated to the unused months
- EU customers are always refunded through the original payment provider
Worth knowing
- The 30-day window is a legal requirement in the EU, not just policy
- Prorated refunds need a support ticket today; self-serve is on the roadmap
Source
- payments-overview.md, refunds section, updated in April
Agents that work while you don't
Describe the job in plain language and get a custom agent: research, reports, monitoring, follow-ups. Run it on demand, on a schedule, or from a webhook, with web search, email, and your connected tools.
Recent
Competitor Watch Agent
Scheduled · Mondays at 9am
Starting the weekly competitor sweep...
Searching the web for launches and pricing changes...
Reading 12 announcements and changelogs...
Writing this week's brief...
Emailing the brief to the team...
Output Preview
Weekly brief: 3 findings
Two competitors moved to usage-based pricing this week.
One shipped an enterprise tier. Full comparison saved to storage and emailed to the team.
Give chat your team's knowledge
Architecture decisions, runbooks, API references, design docs. Upload them to DataHub and chat on the web can search them and cite them in its answers.
Recent
| Name | Size |
|---|---|
Architecture Decisions18 items | — |
Runbooks6 items | — |
Product Specs11 items | — |
api-reference.md | 28 KB |
payments-overview.md | 12 KB |
deploy-runbook.md | 15 KB |
onboarding.md | 6 KB |
schema.sql | 9 KB |
Describe a site. Ship it.
The website builder turns a prompt into a real site: watch it build live, click any text to edit it in place, then publish to your-name.memcode.app or bring a custom domain.
Built the landing page: hero with tasting notes, a story section, and an order CTA wired to the menu.
Working on your site…
Small-batch since 2019
Coffee roasted the slow way
Single-origin lots, roasted to order and shipped within 24 hours of the roast.
Ethiopia Guji
peach · bergamot
Huila Decaf
cocoa · plum
Ember Blend
toffee · citrus
Every frontier model
Different models think differently. Memcode sends each job to the model that handles it best, or you pin one and it handles the whole session. Direct-billed at provider cost, or bring your own keys.
OpenAI
3 modelsGPT-5.6 Sol
thinking1.1M context
OpenAI frontier GPT-5.6 Sol. Top-tier intelligence for coding and professional work, with a 1.05M context window.
GPT-5.6 Terra
thinking1.1M context
Balanced GPT-5.6 model with strong reasoning at a fraction of the cost of Sol.
GPT-5.6 Luna
thinking1.1M context
Fast, cost-effective GPT-5.6 model for quick tasks and high-volume use cases.
Anthropic
4 modelsFable 5
thinking1M context
Anthropic's most capable model: state-of-the-art coding, vision, and computer use with a 1M context window and always-on adaptive thinking.
Opus 5
thinking1M context
Exceptional Claude model for advanced software engineering, with a 1M context window and adaptive thinking.
Sonnet 5
thinking1M context
Latest Claude Sonnet with adaptive thinking, 1M context, and best speed-to-intelligence ratio.
Haiku 4.5
200K context
Fastest and most compact Claude model, perfect for quick responses.
Gemini 3.1 Pro
thinking1M context
Latest Gemini model with significantly improved reasoning and 1M context window.
Gemini 3.6 Flash
thinking1M context
Gemini 3.6 Flash, the latest frontier speed model. Combines frontier intelligence with superior search and grounding; outperforms Gemini 3.1 Pro on coding and agentic benchmarks at a fraction of the cost.
xAI
1 modelGrok 4.5
thinking500K context
xAI flagship model with large context window.
Fireworks
5 modelsGLM-5.2
thinking1M context
Open-weight coding flagship (Z.ai) with a 1M context window — the same cheap lane the memcode CLI runs on.
DeepSeek V4
thinking1M context
DeepSeek's open-weight reasoning and coding model with a 1M context window.
Kimi K2.6
thinking262K context
Moonshot general open-weight model with native vision and a 262K context window.
Kimi K2.7 Code
thinking262K context
Moonshot coding specialist with native vision and a 262K context window.
Kimi K3
thinking1M context
Moonshot flagship on the cheap Fireworks lane: 1M context and native vision.
Open source.
The agent and the gateway are on GitHub under MIT. Self-host it, or let us run it.
One binary, MIT
The agent and the gateway core are one Go module. Read it, fork it, build it.
Self-host it
docker compose up, or point the CLI at any endpoint. No account needed.
No lock-in
Your keys, your models, your data on disk. Leave anytime.
Install in one line
macOS, Linux, and Windows. Runs in your terminal. Open source and self-hostable, or run on Memcode credits, or bring your own keys with any plan.