beadsDistributed graph issue tracker for coding agents on Dolt: dependency-aware beads replace markdown plans — bd ready/claim/close, cell-level merge, push/pull across machines and agents. CLI + MCP.
Why switchSame job — durable spec/task state for coding agents. Trellis bets on markdown living in your repo; beads bets on a Dolt graph DB with merge semantics for multi-agent, multi-machine work.
Full comparison → 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 switchSame bet — durable project knowledge as repo-native markdown. Trellis carries specs, tasks AND journals with auto-injection; brain.md carries only the six-months-out knowledge, through a stricter CLI.
Full comparison → mexA living wiki for your codebase, written by your coding agents: a Tree-sitter graph grounds structured Markdown notes, task-aware routing loads only what's needed, and drift checks catch stale claims.
Why switchTwo in-repo memory conventions for coding agents. Trellis is spec- and task-shaped — conventions, PRDs and journals in `.trellis/` across 20 platforms; mex is knowledge-shaped, with a router, a code graph and drift checks. Process memory versus codebase memory.
Full comparison → okf-agent-memoryGit-native agent memory on Google's OKF v0.2: Markdown+YAML concepts in knowledge/, a zero-dep Go CLI/MCP with <300µs BM25 search, provenance and trust tiers.
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 → bemyagentOne markdown bootstrap file that scaffolds a structured workspace for any coding agent — persistent project docs plus a task tree run through a Think→Task→Execute→Verify cycle with human pacing gates.
Why switchSame insight — persist project structure into the repo so any agent starts with context — at opposite weights: bemyagent is one bootstrap markdown; Trellis is a full spec/task/journal system with sub-agents and 20-platform installers.
Full comparison → three-man-teamA disciplined 3-agent dev process as context files — Architect plans, Builder builds the brief, Reviewer gates — running in one Claude Code session via subagents. Token-frugal by design.
Why switchBoth encode an engineering discipline as repo files: three-man-team is a lightweight Architect/Builder/Reviewer process you read and follow; Trellis enforces its loop with auto-injected specs, task state and journals.
Full comparison →