Mainline

Mainline is a Git-native memory layer that gives AI coding agents access to the engineering intent behind a codebase before they make changes. Rather than letting agents infer why code exists from source alone, Mainline records decisions, abandoned approaches, superseded implementations, reviewer constraints, and explicit risks. It stores them in a local Git-backed store that travels with the repository via custom refs and notes. Agents using Cursor, Claude Code, or OpenAI Codex read Mainline context via hooks that auto-inject the current intent snapshot at every session start, requiring no manual retrieval step from the developer. The CLI provides start, append, and seal commands for recording intent. Setup is minimal: mainline init configures the repo in a single command, installs hooks for supported agents, and is fully operational in under 5 minutes. Pricing is open source and free for the core CLI and protocol under Apache-2.0. Team Cloud (planned, not yet released) will add hosted PR intent summaries, related prior decisions, open risks and anti-patterns, team search over repo memory, and review guardrails for AI-generated changes. Enterprise (planned) will add self-hosted or dedicated deployment, SCM and CI integration, policy controls, audit exports, and support for internal coding agents. No team or enterprise pricing has been published. The GitHub repository (mainline-org/mainline) has 174 stars. MCP is not supported. All data lives in your own Git remote via custom refs and notes, never in a third-party cloud. Mainline is a context and memory layer, not a coding agent. Teams expecting AI-driven code generation must pair it with a separate coding agent such as Cursor, Claude Code, or OpenAI Codex.