v1.0·Open source · MCP-native

The context layer
for AI-native development

Structure your repo, control your context budget, and feed your agents curated lessons and debugging knowledge — all through a single MCP endpoint.

0 lessons curated·last updated 2h ago
claude-code · session
claude "refactor the auth flow"
loading session briefing from maind.dev...
✓ Loaded 3 relevant lessons
L-184 Auth refactor: avoid touching session-store
L-203 Test pattern for OAuth callbacks
L-241 Repo convention: keep handlers thin
I'll start by reading auth/handlers.ts and check how it interacts with the session store...
Compatible with
Claude Code
Claude Desktop
Codex
Cursor
Any MCP client

Install

Two minutes to set up.
Works with whatever you already use.

Pick your client. Paste the snippet. Your agent gets every lesson, ready when it needs them.

Method
bash
claude mcp add maind \
  --transport http \
  https://mcp.maind.dev/mcp \
  --header "Authorization: Bearer ${MAIND_API_KEY}"

Need an API key? Get one free →

How maind works

Three moments where context matters.

Your agent needs different knowledge at different phases. maind delivers the right support at each one.

01

Scan

When your agent reads a prompt, maind identifies the right lessons for the task — narrowed by repo, language, and intent.

02

Shape

As your agent works, maind reminds it to keep the repo AI-ready: good conventions, repo-specific patterns and session boundaries that actually help.

03

Serve

Lessons are injected as context the agent actually reads — not buried in a sidebar. Your code shows the difference.

See it in action

Watch a real session.
maind doing its thing.

An agent starts a task, pulls lessons from maind, and writes code that reflects them. This is what adoption actually looks like.

auth/handlers.ts — claude-code
idle
claude
"add OAuth login to the auth handlers"
1// auth/handlers.ts
2
3
4
5
6
7
8
9
TypeScript · UTF-8
maind briefing
Waiting for query...

Repo readiness

A codebase shaped for
how agents actually read.

Your agent keeps the repo AI-ready as it works — flagging structure gaps, suggesting CLAUDE.md entries, keeping docs honest. You stay in control.

maind / repo-readiness · acme-apiscanning
AI-READINESS SCORE
0
/ 100
Modules documented51%
Convention coverage44%
Session boundariesunclear
FINDINGS
5 open
Missing CLAUDE.md at repo rootopen
47 modules without JSDoc headersopen
Inconsistent naming in /authopen
Overloaded session boundariesopen
Unclear public-vs-internal APIinfo
Agent pulling structure lessons from maind...

Context budget

Smaller context.
Sharper reasoning.

Even with infinite context windows, smaller focused contexts cost less, run faster, and produce better reasoning. maind teaches your agent when to split, summarize, and skip.

maind / context-budget · 30 days
withoutwith maind
0k35k70k105k140kweek 1week 2week 3week 4week 5
Tokens / session
−58%
$0/dev/month saved
Median latency
−0ms
faster responses
Reasoning quality
+0%
fewer wrong steps

Features

Built for how AI agents actually work.

Not another lesson search engine. A structural quality layer that gets more valuable as models get better.

maind / lessons
L-247Avoid /tmp paths in Docker MCPdocker2h
L-246Streamable HTTP timeout defaultsmcp5h
L-245Context budget for repo navcontext1d

Curated AI lessons

A reviewed library of workflow patterns, gotchas, and debugging knowledge — pulled into your agent at the right moment, not as one giant dump.

acme-api / tree
Hover a file to see why maind suggests it.

Repo structure guidance

maind teaches your agent to keep repos AI-ready: clear conventions, CLAUDE.md and AGENTS.md patterns, documentation that pulls its weight.

maind / session
SESSION SIZE
18.6k/ 30k used
saved vs baseline38% · $1/dev/mo
assuming
daily use

Context budget control

Cut token costs, latency, and attention noise. Your agent learns when to split sessions, when to summarize, and what to leave out.

maind / connections
Click a client to see its install snippet.

Works with every MCP client

One endpoint, any client. Streamable HTTP for hosted use, self-hosted Docker image for enterprise on-prem deployments.

Architecture

One MCP call.
Every lesson your agent needs.

Streamable HTTP, served from edge. Sub-80ms p99. Self-hostable for enterprise.

Claude CodeCLIClaude DesktopappCodexCLI + IDECursorIDEMCP SERVERmaind.devEU-westUS-eastAP-southSA-eastUS-westEU-northLIBRARY247 lessonssearch_lessons()Streamable HTTPcurated lessons~80ms p99
p99 latency
< 80ms
Edge regions
6
Self-hostable
Enterprise

Changelog

Shipping every week.

New lessons, features, and infrastructure improvements — tracked so you always know what changed.

View all updates
Apr 18·v1.4.0Feature

Session briefings now support custom instructions

Teams can pin repo-specific lessons to be included in every session briefing. Useful for enforcing conventions across a codebase.

Apr 11·v1.3.2Lessons

14 new lessons on MCP debugging patterns

Community contributions focused on stdio transport pitfalls, OAuth flow debugging, and handling connection resets. All reviewed and curated.

Apr 04·v1.3.0Infra

Sub-80ms p99 latency, now across 6 edge regions

Added edge caching in Frankfurt, São Paulo, and Singapore. Most lesson lookups now return in under one network round-trip.

Mar 28·v1.2.0Feature

Streamable HTTP replaces legacy SSE transport

Migration complete. All clients should update to the new endpoint. Old SSE endpoint deprecated but functional until June.

Pricing

Start free. Scale when you're ready.

Closed beta in progress — paid tiers activate at public launch. Join the Community tier to start now.

Community

Freeforever

For indie devs and small teams.

Get API key
Open-source lessons
All MCP clients supported
Streamable HTTP endpoint
Community contributions
1,000 calls / day
Coming soon

Curated

$29/ month per seat

For teams shipping with AI agents daily.

Join closed beta
Everything in Community
Curated, reviewed lessons
Session briefings
Priority lesson requests
100,000 calls / day
Email support

Enterprise

Customself-hosted available

For regulated industries with data-residency needs.

Talk to sales
Everything in Curated
Self-hosted Docker image
On-prem deployment
Private lesson library
Unlimited calls
SSO + dedicated support
SLA guarantees
Governance layerComing
Per-agent lesson policiesComing

Stop teaching your AI
the same lessons twice.

A growing library of curated AI workflow knowledge — available to your agents the moment they need it.

0 lessons curated·0 active agents today·$0.0M tokens saved this month