Aide

jmylchreest19stars

Multi-agent orchestration, persistent memory, and intelligent workflows for AI coding assistants. Supports Claude Code, OpenCode and Codex.

Autonomous Agents Knowledge Memory

Install Run on PlugMCP

GitHub Website

Run on PlugMCP

1# Aide

README.mdMCP server

Transport: stdio
Status: Local

Power your agent

Add this server

Install from the publisher. Not a PlugMCP endpoint.

Run on PlugMCP

Host a copy with our keys and logs.

No packaged release in the registry yet. Follow the repository README.

RepositoryPublisher installStep-by-step: add this in Claude

Remote URL or a command on your machine? How the two installs differ

Run on PlugMCP

Host a copy with our keys and logs.

A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.

Launch

Server facts

Local

Transport: stdio
License: MIT
Last checked: 2026-10-28

Stars: 19
Tools: —
Uptime: —

Tools

No tool list yet. Remote servers get one after the first health check.

FAQ

Questions

How do I install Aide?

Copy the stdio config for Cursor, Claude Desktop, Claude Code, or VS Code on this page. It uses the publisher's install, not a PlugMCP proxy.

Does Aide need an API key?

No required environment variable is listed on this record.

What transport does Aide use?

Aide runs locally over stdio.

When was Aide last checked?

Last checked 2026-10-28. Multi-agent orchestration, persistent memory, and intelligent workflows for AI coding assistants. Supports Claude Code, OpenCode and Codex.

From the publisher

Documentation

AIDE - AI Development Environment

Persistent memory, code intelligence, and multi-agent orchestration for AI coding assistants. Works with Claude Code, OpenCode, and Codex CLI.

Prerequisite: Bun — the only runtime dependency. The Go binary downloads automatically.

Install

Claude Code:

claude plugin marketplace add jmylchreest/aide
claude plugin install aide@aide

OpenCode:

bunx @jmylchreest/aide-plugin@latest install

Codex CLI:

codex plugin marketplace add jmylchreest/aide
codex plugin add aide@aide
bunx @jmylchreest/aide-plugin@latest install --platform codex   # hooks only — Codex has no plugin hook support

The Codex plugin provides the MCP server and skills (invoke with $<name> or /skills); the install step adds lifecycle hooks. On older Codex versions without plugin support, the install step alone configures everything.

The Go binary ships as a per-platform npm package, so it lands on disk with the install (older setups fall back to downloading it on first run). Skills become available immediately.

Install pins the exact version in opencode.json; re-run it with @latest to upgrade. See OpenCode setup for why the pin matters.

What You Get

Capability	What it does
Memory	Remembers preferences and context across sessions
Decisions	Records architectural choices, enforces them in every session
Blueprints	Seeds best-practice decisions for Go, Rust, GitHub Actions, and more
Code Index	Fast symbol search, call graphs, and references via tree-sitter
Static Analysis	Detects complexity, coupling, secrets, and code duplication
Survey	Maps codebase structure: modules, entry points, tech stack, churn hotspots
Skills	23 built-in workflows triggered by natural language
Swarm	Parallel agents with full SDLC pipelines (design, test, implement, verify, docs)
34 MCP Tools	Full programmatic access to all capabilities above

Get Started

Existing project — understand the codebase:

Survey this codebase and help me understand its structure.

AIDE indexes symbols, discovers modules, tech stack, entry points, and git churn hotspots, then presents the big picture. Full guide

New project — set up guardrails:

Bootstrap with curated best practices, then customise:

aide blueprint import go go-github-actions    # seeds decisions from blueprints
aide blueprint import --detect               # or auto-detect from project markers

Then refine with the decide skill for project-specific choices:

Help me decide on the auth strategy and database schema for this project.

Blueprints cover language idioms, tooling, CI/CD, and common pitfalls. The decide skill handles project-specific architectural choices. Both persist across every future session. Full guide

Share decisions with your team:

Export decisions and memories to git-friendly markdown, then commit them:

aide share export      # writes to .aide/shared/
git add .aide/shared && git commit -m "share: team decisions"

Teammates who add AIDE_SHARE_AUTO_IMPORT=1 to .claude/settings.json get them imported automatically at session start. Decisions are append-only per topic (new ones supersede, history kept); memories merge by ULID (newer edits win).

Teammates without AIDE can still use the folder. Each .aide/shared/decisions/*.md and .aide/shared/memories/*.md is self-contained markdown with structured frontmatter — any AI assistant can ingest them as context. A short DECISIONS.md / MEMORIES.md explainer is written alongside the exports to document the format. Full guide

Skills

Skills are markdown workflows triggered by keywords. Type naturally — trigger matching is fuzzy.

Skill	Example Prompt	What Happens
swarm	`swarm 3 implement dashboard`	Parallel agents with SDLC pipeline per story
plan-swarm	`plan swarm for the dashboard`	Decomposes work into stories for swarm execution
decide	`help me decide on auth strategy`	Structured decision interview, records choices
design	`design the auth system`	Technical spec with interfaces and acceptance criteria
survey	`survey this codebase`	Maps modules, tech stack, entry points, and churn
test	`write tests for auth`	Test suite with coverage verification
implement	`implement the feature`	TDD — make failing tests pass
verify	`verify the implementation`	Full QA: tests, lint, types, build, debug artifacts
docs	`update the documentation`	Updates docs to match implementation
autopilot	`autopilot fix all failing tests`	Persistent — won't stop until verified complete
build-fix	`fix the build errors`	Iteratively fixes build/lint/type errors
debug	`debug why login fails`	Systematic debugging with hypothesis testing
perf	`optimize the API`	Performance profiling and optimization
review	`review this PR`	Security-focused code review
patterns	`check code health`	Surface code quality issues via static analysis
assess-findings	`assess findings`	Triage: read code, accept noise, keep real issues
code-search	`find all auth functions`	Search symbols, find call sites
memorise	`remember I prefer vitest`	Stores info for future sessions
recall	`do you remember the testing decision?`	Searches memories and decisions
forget	`forget the old auth decision`	Soft-delete or hard-delete memories
git	`create a worktree for this feature`	Git operations and worktree management
worktree-resolve	`merge worktrees`	Merges worktree branches with conflict resolution
context-usage	`how much context am I using?`	Analyze session context and token usage

Custom skills: Create .aide/skills/my-skill.md with YAML frontmatter (name, triggers) and markdown body. Auto-discovered from .aide/skills/ > skills/ > plugin-bundled > ~/.aide/skills/.

Configuration

Variable	Description
`AIDE_DEBUG=1`	Enable debug logging (logs to `.aide/_logs/`)
`AIDE_FORCE_INIT=1`	Force initialization in non-git directories
`AIDE_CODE_WATCH=1`	Enable file watching for auto-reindex
`AIDE_CODE_WATCH_DELAY=30s`	Delay before re-indexing after file changes
`AIDE_INDEX_NON_VCS=1`	Allow watcher/indexing in non-VCS dirs (default: refuse)
`AIDE_INDEX_WORKERS=N`	Parallel parser workers for code indexing (default: NumCPU, capped at 32)
`AIDE_MEMORY_INJECT=0`	Disable memory injection
`AIDE_MEMORY_SCORING_DISABLED=1`	Disable memory scoring (use chronological order)
`AIDE_MEMORY_DECAY_DISABLED=1`	Disable recency decay in memory scoring
`AIDE_SHARE_AUTO_IMPORT=1`	Auto-import shared decisions/memories on start

CLI Reference

aide status                               # System dashboard
aide code index                           # Index codebase symbols
aide code search "getUser"                # Search symbols
aide survey run                           # Map codebase structure
aide findings run all                     # Run all static analysers
aide findings stats                       # Health overview
aide findings list --severity=critical    # View critical findings
aide version                              # Check binary version

aide-web

Optional web dashboard for monitoring aide daemon instances — status, memories, decisions, findings, code search, and more.

Download: Latest release

Platform	Binary
Linux x64	aide-web-linux-amd64
Linux arm64	aide-web-linux-arm64
macOS x64	aide-web-darwin-amd64
macOS arm64	aide-web-darwin-arm64
Windows x64	aide-web-windows-amd64.exe
Windows arm64	aide-web-windows-arm64.exe

aide-web --port 8080 --open

Documentation

Full documentation: jmylchreest.github.io/aide

Architecture — Layered design, hooks, MCP read/write separation
MCP Tools — All 34 tools: memory, decisions, code, findings, survey, tasks, tokens
CLI Reference — Full command reference
Swarm Mode — SDLC pipeline, worktrees, agent coordination
Skills — Built-in and custom skill reference
Storage — File layout, sharing via git

Advanced Installation

Claude Code — Marketplace for Teams

Register the marketplace in ~/.claude/settings.json (or .claude/settings.json for project-level) so team members are prompted to install:

{
  "extraKnownMarketplaces": {
    "aide": {
      "source": {
        "source": "github",
        "repo": "jmylchreest/aide"
      }
    }
  }
}

Claude Code — Permissions

Add to ~/.claude/settings.json:

{
  "permissions": {
    "allow": [
      "Bash(aide *)",
      "Bash(**/aide *)",
      "Bash(git worktree *)",
      "mcp__plugin_aide_aide__*"
    ]
  }
}

From Source

git clone https://github.com/jmylchreest/aide && cd aide

# Build (requires Go 1.25+ and Bun)
cd aide && go build -o ../bin/aide ./cmd/aide && cd ..
bun install && bun run build

# Claude Code
claude --plugin-dir /path/to/aide

# OpenCode
bunx @jmylchreest/aide-plugin@latest install --project

Troubleshooting

aide version                              # Check binary
aide status                               # Full system dashboard
AIDE_DEBUG=1 claude                       # Debug logging (or AIDE_DEBUG=1 opencode)

Reinstall:

# Claude Code
claude plugin uninstall aide && claude plugin install aide@aide

# OpenCode
bunx @jmylchreest/aide-plugin@latest uninstall && bunx @jmylchreest/aide-plugin@latest install

Adding Support for New Assistants

See the adapters documentation. AIDE's adapter architecture maps any tool's lifecycle events to shared core functions — skills and MCP tools work out of the box.

License

MIT

Aide

jmylchreest19stars

Multi-agent orchestration, persistent memory, and intelligent workflows for AI coding assistants. Supports Claude Code, OpenCode and Codex.

Autonomous Agents Knowledge Memory

Install Run on PlugMCP

GitHub Website

Run on PlugMCP

1# Aide

README.mdMCP server

Transport: stdio
Status: Local

Power your agent

Add this server

Install from the publisher. Not a PlugMCP endpoint.

Run on PlugMCP

Host a copy with our keys and logs.

No packaged release in the registry yet. Follow the repository README.

RepositoryPublisher installStep-by-step: add this in Claude

Remote URL or a command on your machine? How the two installs differ

Run on PlugMCP

Host a copy with our keys and logs.

A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.

Launch

Server facts

Local

Transport: stdio
License: MIT
Last checked: 2026-10-28

Stars: 19
Tools: —
Uptime: —

Tools

No tool list yet. Remote servers get one after the first health check.

FAQ

Questions

How do I install Aide?

Copy the stdio config for Cursor, Claude Desktop, Claude Code, or VS Code on this page. It uses the publisher's install, not a PlugMCP proxy.

Does Aide need an API key?

No required environment variable is listed on this record.

What transport does Aide use?

Aide runs locally over stdio.

When was Aide last checked?

Last checked 2026-10-28. Multi-agent orchestration, persistent memory, and intelligent workflows for AI coding assistants. Supports Claude Code, OpenCode and Codex.

From the publisher

Documentation

AIDE - AI Development Environment

Persistent memory, code intelligence, and multi-agent orchestration for AI coding assistants. Works with Claude Code, OpenCode, and Codex CLI.

Prerequisite: Bun — the only runtime dependency. The Go binary downloads automatically.

Install

Claude Code:

claude plugin marketplace add jmylchreest/aide
claude plugin install aide@aide

OpenCode:

bunx @jmylchreest/aide-plugin@latest install

Codex CLI:

codex plugin marketplace add jmylchreest/aide
codex plugin add aide@aide
bunx @jmylchreest/aide-plugin@latest install --platform codex   # hooks only — Codex has no plugin hook support

The Go binary ships as a per-platform npm package, so it lands on disk with the install (older setups fall back to downloading it on first run). Skills become available immediately.

Install pins the exact version in opencode.json; re-run it with @latest to upgrade. See OpenCode setup for why the pin matters.

What You Get

Capability	What it does
Memory	Remembers preferences and context across sessions
Decisions	Records architectural choices, enforces them in every session
Blueprints	Seeds best-practice decisions for Go, Rust, GitHub Actions, and more
Code Index	Fast symbol search, call graphs, and references via tree-sitter
Static Analysis	Detects complexity, coupling, secrets, and code duplication
Survey	Maps codebase structure: modules, entry points, tech stack, churn hotspots
Skills	23 built-in workflows triggered by natural language
Swarm	Parallel agents with full SDLC pipelines (design, test, implement, verify, docs)
34 MCP Tools	Full programmatic access to all capabilities above

Get Started

Existing project — understand the codebase:

Survey this codebase and help me understand its structure.

AIDE indexes symbols, discovers modules, tech stack, entry points, and git churn hotspots, then presents the big picture. Full guide

New project — set up guardrails:

Bootstrap with curated best practices, then customise:

aide blueprint import go go-github-actions    # seeds decisions from blueprints
aide blueprint import --detect               # or auto-detect from project markers

Then refine with the decide skill for project-specific choices:

Help me decide on the auth strategy and database schema for this project.

Blueprints cover language idioms, tooling, CI/CD, and common pitfalls. The decide skill handles project-specific architectural choices. Both persist across every future session. Full guide

Share decisions with your team:

Export decisions and memories to git-friendly markdown, then commit them:

aide share export      # writes to .aide/shared/
git add .aide/shared && git commit -m "share: team decisions"

Skills

Skills are markdown workflows triggered by keywords. Type naturally — trigger matching is fuzzy.

Skill	Example Prompt	What Happens
swarm	`swarm 3 implement dashboard`	Parallel agents with SDLC pipeline per story
plan-swarm	`plan swarm for the dashboard`	Decomposes work into stories for swarm execution
decide	`help me decide on auth strategy`	Structured decision interview, records choices
design	`design the auth system`	Technical spec with interfaces and acceptance criteria
survey	`survey this codebase`	Maps modules, tech stack, entry points, and churn
test	`write tests for auth`	Test suite with coverage verification
implement	`implement the feature`	TDD — make failing tests pass
verify	`verify the implementation`	Full QA: tests, lint, types, build, debug artifacts
docs	`update the documentation`	Updates docs to match implementation
autopilot	`autopilot fix all failing tests`	Persistent — won't stop until verified complete
build-fix	`fix the build errors`	Iteratively fixes build/lint/type errors
debug	`debug why login fails`	Systematic debugging with hypothesis testing
perf	`optimize the API`	Performance profiling and optimization
review	`review this PR`	Security-focused code review
patterns	`check code health`	Surface code quality issues via static analysis
assess-findings	`assess findings`	Triage: read code, accept noise, keep real issues
code-search	`find all auth functions`	Search symbols, find call sites
memorise	`remember I prefer vitest`	Stores info for future sessions
recall	`do you remember the testing decision?`	Searches memories and decisions
forget	`forget the old auth decision`	Soft-delete or hard-delete memories
git	`create a worktree for this feature`	Git operations and worktree management
worktree-resolve	`merge worktrees`	Merges worktree branches with conflict resolution
context-usage	`how much context am I using?`	Analyze session context and token usage

Configuration

Variable	Description
`AIDE_DEBUG=1`	Enable debug logging (logs to `.aide/_logs/`)
`AIDE_FORCE_INIT=1`	Force initialization in non-git directories
`AIDE_CODE_WATCH=1`	Enable file watching for auto-reindex
`AIDE_CODE_WATCH_DELAY=30s`	Delay before re-indexing after file changes
`AIDE_INDEX_NON_VCS=1`	Allow watcher/indexing in non-VCS dirs (default: refuse)
`AIDE_INDEX_WORKERS=N`	Parallel parser workers for code indexing (default: NumCPU, capped at 32)
`AIDE_MEMORY_INJECT=0`	Disable memory injection
`AIDE_MEMORY_SCORING_DISABLED=1`	Disable memory scoring (use chronological order)
`AIDE_MEMORY_DECAY_DISABLED=1`	Disable recency decay in memory scoring
`AIDE_SHARE_AUTO_IMPORT=1`	Auto-import shared decisions/memories on start

CLI Reference

aide status                               # System dashboard
aide code index                           # Index codebase symbols
aide code search "getUser"                # Search symbols
aide survey run                           # Map codebase structure
aide findings run all                     # Run all static analysers
aide findings stats                       # Health overview
aide findings list --severity=critical    # View critical findings
aide version                              # Check binary version

aide-web

Optional web dashboard for monitoring aide daemon instances — status, memories, decisions, findings, code search, and more.

Download: Latest release

Platform	Binary
Linux x64	aide-web-linux-amd64
Linux arm64	aide-web-linux-arm64
macOS x64	aide-web-darwin-amd64
macOS arm64	aide-web-darwin-arm64
Windows x64	aide-web-windows-amd64.exe
Windows arm64	aide-web-windows-arm64.exe

aide-web --port 8080 --open

Documentation

Full documentation: jmylchreest.github.io/aide

Architecture — Layered design, hooks, MCP read/write separation
MCP Tools — All 34 tools: memory, decisions, code, findings, survey, tasks, tokens
CLI Reference — Full command reference
Swarm Mode — SDLC pipeline, worktrees, agent coordination
Skills — Built-in and custom skill reference
Storage — File layout, sharing via git

Advanced Installation

Claude Code — Marketplace for Teams

Register the marketplace in ~/.claude/settings.json (or .claude/settings.json for project-level) so team members are prompted to install:

{
  "extraKnownMarketplaces": {
    "aide": {
      "source": {
        "source": "github",
        "repo": "jmylchreest/aide"
      }
    }
  }
}

Claude Code — Permissions

Add to ~/.claude/settings.json:

{
  "permissions": {
    "allow": [
      "Bash(aide *)",
      "Bash(**/aide *)",
      "Bash(git worktree *)",
      "mcp__plugin_aide_aide__*"
    ]
  }
}

From Source

git clone https://github.com/jmylchreest/aide && cd aide

# Build (requires Go 1.25+ and Bun)
cd aide && go build -o ../bin/aide ./cmd/aide && cd ..
bun install && bun run build

# Claude Code
claude --plugin-dir /path/to/aide

# OpenCode
bunx @jmylchreest/aide-plugin@latest install --project

Troubleshooting

aide version                              # Check binary
aide status                               # Full system dashboard
AIDE_DEBUG=1 claude                       # Debug logging (or AIDE_DEBUG=1 opencode)

Reinstall:

# Claude Code
claude plugin uninstall aide && claude plugin install aide@aide

# OpenCode
bunx @jmylchreest/aide-plugin@latest uninstall && bunx @jmylchreest/aide-plugin@latest install

Adding Support for New Assistants

See the adapters documentation. AIDE's adapter architecture maps any tool's lifecycle events to shared core functions — skills and MCP tools work out of the box.

License

MIT