sqlew

by sqlew-io

Not rated
GitHub

About

ADR (Architecture Decision Record) for AI Agents – An MCP server that enables AI agents to create, query, and maintain architecture decision records in a structured SQL database

Details

Author
sqlew-io
Categories
Developer Tools, Other

Setup

Install sqlew in your MCP client (Claude Desktop, Cursor, Windsurf, and others).

Repository: https://github.com/sqlew-io/sqlew

Follow the installation instructions in the repository README, then restart your MCP client.

Strong coding agents no longer "forget" the stack between sessions the way older models did. They treat thecodebase as ground truth— and that is good for correctness.

The new failure mode is cost and thrash:

- Specs, plans, and ADRs already saywhya choice was made
- The agent still re-opens large swaths of source "just to be sure"
- Rejected alternatives and non-local constraints are expensive (or impossible) to re-derive from code alone
- Every turn pays the same investigation tax; multi-agent and multi-day work multiplies it

Code answerswhat is implemented. It is a poor, high-token index forwhy we chose it,what we forbade, andwhat we already rejected.

sqlew is an MCP server that storesarchitectural decisions and constraintsin a SQL database — with rationale, tags, layers, and rejected alternatives. Agentsquery intent first(suggest, session context, targeteddecision/constraintlookups) instead of re-deriving design context from a full-tree read every turn.

┌──────────────────────────────────────────────────────────────────────┐ │ Without sqlew │ With sqlew │ │────────────────────────────────────────│─────────────────────────────│ │ Plan/spec: "use Postgres, no Mongo" │ Plan approved → ADR saved │ │ Next turn: re-read half the repo │ Next turn: suggest/query │ │ "just to confirm the architecture" │ → intent in milliseconds │ │ Tokens burned; same audit next agent │ Code read only for the diff│ └──────────────────────────────────────────────────────────────────────┘

- Capture— Plan Mode + hooks record decisions/constraints when you approve a plan (zero extra ceremony with sqlew-plugin)
- Recall— Session start injects recent context (where the harness supports it);suggestfinds related ADRs before the agent expands search
- Enforce— Constraints stay first-class rules; duplicate/similarity checks stop circular re-decisions

Built on theModel Context Protocol(MCP), so it works with any MCP-compatible AI coding tool.

This software does not send any data to external networks. We NEVER collect any data or usage statistics.

npm 12+(bundled with Node 24.19+) blocks dependency install scripts by default. sqlew needsbetter-sqlite3to download or compile its native addon, so allow that script:

npm install -g --allow-scripts=better-sqlite3 sqlew

Without the flag,sqlewinstalls but exits on first run withCould not locate the bindings file. Re-run the command above to repair an existing install.

npm 11 and earlier still run install scripts by default;npm install -g sqlewis enough there.

Choose the setup that matches your environment. Each client has its own install and uninstall steps.

claude plugin marketplace add sqlew-io/sqlew-plugin claude plugin install sqlew

Configures MCP server, Skills (Plan Mode guidance), and Hooks (automatic decision capture).

codex plugin marketplace add sqlew-io/sqlew-plugin codex plugin install sqlew --source sqlew-plugin

After install, open/hooksin Codex and trust the bundled sqlew hooks. Enable Plan Mode withcollaboration_modes = trueunder[features]in your Codex config.

Do not duplicate skills in~/.codex/skills/or add[mcp_servers.sqlew]toconfig.tomlwhen using the plugin. SeeHooks Guide.

grok plugin install sqlew-io/sqlew-plugin --trust grok plugin update

Configures MCP server, Skills (plan mode guidance), and Hooks (automatic decision capture onexit_plan_mode).

Do not duplicate hooks in~/.grok/hooks/or add[mcp_servers.sqlew]to~/.grok/config.toml. SeeHooks Guide.

Requires sqlew>= 5.3.0. Hermes uses a separate plugin bundle (.hermes-plugin/), not the Claude/Codex plugin manifest.

hermes plugins install sqlew-io/sqlew-plugin/.hermes-plugin hermes plugins enable sqlew

Merges MCP + shell hooks into~/.hermes/config.yamland copies planning skills to~/.hermes/skills/. SeeHermes Hooks Guidefor wire-protocol details and manualconfig.yamlsetup.

If you merged hooks manually before using the plugin, also removemcp_servers.sqlewand sqlewhooks:entries from~/.hermes/config.yaml. Skills under~/.hermes/skills/sqlew-are not removed automatically.

Requires sqlew with thesqlew/hooksexport (seeHarness Compatibilityfor the minimum version). omp uses an in-processExtension(.omp-plugin/), not Claude-style shell hooks.

npm i -g --allow-scripts=better-sqlite3 sqlew # see Install above (npm 12+) omp --extension /path/to/sqlew-plugin/.omp-plugin # or: omp plugin install /path/to/sqlew-plugin/.omp-plugin

Session context viabefore_agent_start; Plan-to-ADR when you approve viaxd://propose//xdev/propose. Plans live as session-locallocal://-plan.md(no project.sqlew/plans/copy by default). SeeHooks Guide.

MCP still comes from the project.mcp.json(Extension does not re-register MCP when already present).

MCP server only — no sqlew-plugin hooks or skills (Cursor, Claude Desktop, custom clients, …). SeeHarness Compatibility.

{ "mcpServers": { "sqlew": { "command": "sqlew" } } }

The database (~/.config/sqlew/sqlew-shared.db) and config are auto-created on first run. SeeShared Databasefor details.

That's it. Every time you create a plan and get user approval, your architectural decisions areautomatically recorded.

No special commands needed — just plan your work normally, and sqlew captures the decisions in the background.

Not every feature works the same on every client.Grok Builduses passive hooks (no stdout injection), so session context and plan-mode hook enforcement are skill-based only (◎).oh-my-pi (omp)uses an in-process Extension (sqlew/hooks) rather than shell hooks — the summary rows below are full (✓).

✓ full · △ partial · ◎ skills only · ✎ manual MCP · — not available

Full matrix (hooks,Other harnesscolumn, fallbacks):Harness Compatibility

Connect tosqlew.iofor team-shared decisions:

# ~/.config/sqlew/.sqlew.env (shared across all projects) SQLEW_API_KEY=your-api-key
# .sqlew/config.toml [database] type = "cloud" [project] name = "your-project-name"

- All team members share the same decision database
- Works seamlessly with Git worktree workflows
- No local database setup required

- Architecture Evolution— Document major decisions with full context and alternatives considered
- Pattern Standardization— Establish coding patterns as constraints, enforce via AI code generation
- Cross-Session Continuity— Agents reuse recorded intent across days without re-auditing the tree forwhy
- Multi-Agent Coordination— Multiple AI agents share architectural understanding
- Onboarding Acceleration— New sessions/agents load decisions and constraints first, then read only the code paths that matter

- Migrating to SaaS— Export local data to sqlew.io cloud

8 action-based tools:decision,constraint,project,suggest,help,example,use_case,queue

All tools supportaction: "help"for documentation. Theprojecttool targets a project per call for desktop AI agents (Claude Desktop, Hermes Desktop) — seeShared Database.

Support development viaGitHub Sponsors.

- Hermes support— Plan-to-ADR viasqlew-plugin.hermes-pluginbundle (hermes plugins install sqlew-io/sqlew-plugin/.hermes-plugin)
- Hook normalization— Hermespre_tool_call/pre_llm_callpayloads mapped to canonical Claude-shaped events and tools
- Every-turn plan guidanceon-promptinjects FULL/SHORT context via Hermespre_llm_call({"context":"..."})
- .hermes/plans/— Plan files written by the Hermesplanskill are tracked for decision extraction

Apache License 2.0 — Free for commercial and personal use. SeeLICENSEfor details.

- npm package
-
Issues
-
Model Context Protocol

Built withMCP SDK,better-sqlite3, and TypeScript.

This is a web browser that enables your coding agent, such as Claude Code, to visit websites on your behalf and assist you in identifying bugs or creating UI test cases.

Anchor is local repo and org memory for AI coding agents. It indexes GitHub PR history, current code, tests, regressions, architecture, and cross-repo impact locally, then exposes concise cited context through MCP and CLI workflows. Local-first. Read-only GitHub access. No CLI telemetry. No SaaS. No remote LLM calls.

Design system MCP server — query tokens, components, icons, and WCAG contrast data from Git-backed design systems.

Provides code context from local git repositories.

Local-first documentation for AI agents. Indexes docs from any git repo into SQLite for offline, instant, private access to up-to-date library documentation.

DOS is a small open-source kernel that doesn't believe your AI agents: it verifies what actually shipped from git evidence, arbitrates file collisions between parallel agents, and refuses with structured reasons.

Prevents regression by providing Blast Radius data to AI based on your git history

Fabrx is a no-code platform where users can setup custom document processing workflows

Model Context Protocol (MCP) server for GitLab — exposes 1006 GitLab REST & GraphQL API operations as MCP tools (28 meta-tools / 43 enterprise), 24 resources, 38 prompts, and 17 completion types for AI assistants. Written in Go, single static binary, stdio and HTTP transport.

kemdiCode MCP is a Model Context Protocol server that gives AI agents and IDE assistants access to 124 specialized tools for code analysis, generation, git operations, file management, AST-aware editing, project memory, cognition & self-improvement, multi-board kanban, and multi-agent coordination.

No reviews yet — be the first

Sign in to leave a review

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.