Which agents does it work with?
`aoci init` recognizes Claude Code, Codex, Cursor, and OpenCode. Any other host that supports stdio MCP can use the configuration in the Config tab.
@aoci-spec
Basic information
Local MCP server and CLI that keeps a Git-versioned, model-written index of a codebase and its database schema, so coding agents start each task with the whole system in view.
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"aoci": {
"command": "/absolute/path/to/aoci",
"args": [
"--repo",
"/absolute/path/to/your/project",
"mcp"
]
}
}
}Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
AOCI-CODE gives coding agents a persistent, Git-versioned map of the whole codebase, written by the agent and kept aligned with the code.
AOCI-CODE is a local MCP server and CLI, written in Go, that keeps a persistent, Git-versioned index of a codebase for coding agents such as Claude Code, Codex, Cursor, and OpenCode. The agent writes one line per file: what it is responsible for, which files must be read with it, what callers depend on, and the constraints that can't be inferred from the code. Agents read the whole index before a task instead of re-reading the repository every time.
aoci init and aoci scan in your project. init writes the MCP configuration for Claude Code, Codex, and OpenCode; for Cursor, paste the configuration from the Config tab.aoci_rules: returns the session runtime contract for the current AOCI version.aoci_overview: delivers the complete index, in chunks when it is large, and checks receipt with a sampled challenge.aoci_header: returns the tag dictionary, FRAS rules, and calibration examples.aoci_search: searches entries by keyword or tag.aoci_get_entries: reads specific entries by path, directory, or object reference.aoci_maintain: after code changes settle, returns the next batch of entries that need updating.aoci_update_entry: submits a complete batch of model-written entries through an atomic, recoverable write.aoci_remove_entry: removes an entry whose source object no longer exists.aoci_report: records a follow-up note when evidence is insufficient to write an entry, Legacy layout only.`aoci init` recognizes Claude Code, Codex, Cursor, and OpenCode. Any other host that supports stdio MCP can use the configuration in the Config tab.
No. The index gives the agent a picture of the whole system, and precise lookup tools fetch exact code while it works. They can be used together.
FSL-1.1-MIT. It is source-available, and each version becomes MIT two years after its release.

Open-source Python SDK & MCP interface for Priostack Agent Context Network (ACN). Zero-setup, autonomous memory orchestration for AI agents.

The Cloud is the AI-native workspace that gives every AI — Claude, ChatGPT, Gemini, and other Frontier & Free or Local models — shared memory and real agents. Not cloud computing: thecloud.so is one workspace where your

Sooveryn gives Claude Code a team of AI personas that remembers your project. Soov, the partner and team lead, keeps your decisions and how you work in a lasting memory, and finds them again by words and by meaning, from
Memlord is a remote MCP server available at https://app.memlord.com.

MCP connector for Snipara, the Project Brain for AI coding agents
Comments