brain.mdFile-based durable memory for coding agents: brain-setup scaffolds a BRAIN.md protocol + brain/ directory of decisions, requirements and constraints — plain Markdown in your repo, written via CLI.
Why switchBoth keep coding-agent memory as plain Markdown in the repo; brain.md is a protocol you scaffold and maintain by hand, OKF adds a spec (frontmatter provenance/trust/lifecycle) plus a Go validator, BM25 search and MCP server.
Full comparison → TrellisSpec, task and memory layer that lives in your repo: .trellis/ holds conventions, PRDs and journals, auto-injected each session — one workflow across 20 coding-agent platforms.
Why switchSame in-repo, git-versioned memory idea: trellis holds conventions, PRDs and journals in .trellis/ and auto-injects them; OKF holds typed concepts with a link graph and lets the agent search rather than inject everything.
Full comparison → ai-memoryRust long-term memory server for coding CLIs: lifecycle hooks capture sessions into a sanitized shared wiki, then hand a bounded summary to the next agent so Codex can resume what Claude Code started.
Why switchai-memory captures sessions into a shared wiki via hooks and serves it from a Rust server; OKF is the opposite posture — deliberate, reviewed concept authoring with no capture pipeline and no daemon.
Full comparison → memsearchZilliz's unified memory for coding agents: one Markdown + Milvus store shared across Claude Code, Codex, OpenCode and OpenClaw — hybrid search, plus repeated workflows distilled into skills.
Why switchmemsearch also stores memory as Markdown but retrieves through Milvus embeddings; OKF stays lexical (BM25) and dependency-free, trading semantic recall for zero infra and zero API cost.
Full comparison →