cli
Active·★ 66·Apache-2.0·Updated 2026-09-22
Archcore CLI provides a Git-native context layer for AI coding agents, storing project knowledge like architecture decisions and rules within a `.archcore/` directory, versioned with your code. This ensures agents load relevant, structured context at session start, improving their ability to follow conventions and decisions, and enabling new decisions to be recorded as durable context.
#AI Agents#Context Management#Dev Tooling#Knowledge Base#Git-Native#Structured Documentation#Architecture Decisions
01
Features
01Provides git-native, version-controlled project context for AI agents.
02Manages structured knowledge (ADRs, rules, plans) as typed Markdown documents with YAML frontmatter.
03Ships as a CLI and local stdio MCP server, enabling compatibility with various AI coding agents.
04Automates agent integration by scaffolding `.archcore/` and wiring up hooks and MCP configurations.
02
Compatibility
Go
Runtime
Verified via docs
macOS
Platform
Verified via docs
Linux
Platform
Verified via docs
Windows
Platform
Verified via docs
MCP
Standard
Verified via docs
Claude Code
AI Agent
Verified via docs
03
Quick start
1
$ curl -fsSL https://archcore.ai/install.sh | bash
04
Use cases
↳Ensuring AI agents follow established architecture decisions and coding conventions.
↳Recording new technical decisions or rules as durable, versioned context for future sessions.
↳Documenting incidents and their prevention steps, making them accessible to agents during relevant tasks.
↳Providing specific contextual information (e.g., relevant ADRs, rules) to agents before they modify a module.
05
Alternatives
okf-agent-memory★ 827
Git-native persistent memory for AI coding agents. Implements Google OKF v0.2 with sub-300µs in-memory BM25 search, embedded MCP server, and progressive disclosure. Slashes token bloat by 80% with zero external databases or dependencies. Built in pure Go.
lockkeeper★ 17
Skill router and prompt-injection firewall for AI coding agents: gives Claude Code, Codex and Cursor the few skills, MCP servers and tools each task needs.
sync★ 7
The agent harness you steer — structured context, automatic staleness gates, and block-by-block review, all bound to your code. Local-first, MCP-native, open source.
mori★ 32
mori MCP server — A shared memory layer for AI coding agents — one that compounds.
fava-trails★ 26
🫛👣 FAVA Trails — Git-native, curated memory for AI agents via MCP. Draft isolation, promotion gate, thought lifecycle hooks, memory curation protocols, supersession chains.
agents-remember★ 29
`Agents Remember` is a Drift-aware repository memory for coding agents in complex codebases. Captures what code can't say on its own! Retrieves memory by path, semantic search, and relationship (code-graph).
Comments
Log in to leave a comment
No comments yet. Be the first!