pro-workflowOne SQLite store under every Claude Code session: corrections become FTS5-searchable rules that auto-load, research grows persistent wikis, and 37 hook scripts add quality gates.
Why switchSame core job — corrections that stick across Claude Code sessions. claude-reflect is the focused plugin (corrections → CLAUDE.md); pro-workflow builds a whole SQLite-backed memory-and-hooks platform around the idea.
Full comparison → agentic-context-engineLearning loop for any agent: reflect on failures, distill strategies into a Skillbook, inject them next run — 2x consistency on Tau2, 49% token cuts. LiteLLM-based, 100+ providers.
Why switchSame learn-from-corrections loop at different scopes: claude-reflect is a Claude Code plugin syncing learnings into CLAUDE.md; ACE is a framework-level engine for any agent you build, with strategies as first-class objects.
Full comparison → ECCCross-harness 'operating system' for coding agents — 268 skills, 66 agents, hooks, rules, memory persistence, instinct-based continuous learning and AgentShield security scanning. MIT.
Why switchBoth close the learning loop from your corrections: claude-reflect is a focused Claude Code plugin syncing approved learnings to CLAUDE.md; ECC's instinct system does the same continuous-learning job with confidence scoring inside a much larger harness framework.
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 switchBoth mine your sessions into reusable assets: claude-reflect captures corrections into CLAUDE.md and /reflect-skills commands for Claude Code; memsearch's skills-from-memory does the same distillation continuously, across four agent platforms.
Full comparison → AcontextSkill memory layer for agents: auto-captures learnings from runs into plain Markdown skill files you can read, edit, git and share across frameworks — memory without an opaque store.
Why switchclaude-reflect does the same capture-corrections-into-CLAUDE.md/skills loop but is a Claude Code plugin with human-approved syncing; Acontext is framework-agnostic and automatic. Deep in Claude Code → reflect; multi-framework or building your own agent → Acontext.
Full comparison → SkillXResearch framework that auto-distills agent trajectories into a three-level skill knowledge base (planning, functional, atomic) — pluggable into weaker agents and new environments.
Why switchBoth turn agent experience into reusable knowledge: claude-reflect captures your corrections into CLAUDE.md pragmatically, SkillX distills full trajectories into a transferable skill hierarchy — research-grade.
Full comparison → coreSelf-hosted, always-on "personal AI OS": watches your apps, keeps a persistent memory graph, and acts autonomously within guardrails — a product, not a library for building agents.
Why switchBoth chase memory that compounds: core builds a full personal-AI OS with a persistent memory graph; claude-reflect does one narrow slice — your coding agent's lessons — with zero infrastructure.
Full comparison → opencode-memOpenCode plugin giving coding agents persistent cross-session memory — local SQLite + vector search, automatic memory capture, user-profile learning, and a web UI. Nothing leaves your machine.
Why switchBoth close the cross-session learning loop for coding agents: claude-reflect distills your corrections into CLAUDE.md via /reflect; opencode-mem auto-captures work into a searchable vector store and injects relevant memories per session.
Full comparison →