StackMap
Subscribe

Acontext vs claude-reflect

Skill 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. — versus — Claude Code plugin that learns from your corrections — hooks capture them in-session, /reflect syncs approved learnings to CLAUDE.md/AGENTS.md, /reflect-skills mines history into reusable commands.

The curated verdict

claude-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.

Acontextclaude-reflect
Stars3.6k1.3k
Forks331108
LanguageJavaScriptPython
LicenseApache-2.0MIT
Last activity20 days ago4 months ago
Topicsmemory, skillscoding, memory
Curated connections412

Acontext — the curator's take

The "memory should be legible" bet: instead of embeddings in a vector store, learnings from agent runs become Markdown skill files you can read, diff, git and mount into any framework — debuggable memory users can inspect and correct, the exact thing opaque memory layers get wrong. It can also adopt and evolve skills you wrote or downloaded. Trade-off: no semantic recall over thousands of entries; it lives or dies on distilling runs into a curated, manageable skill set. Want scale-out retrieval memory instead? That's memmachine or hindsight territory.

claude-reflect — the curator's take

Install claude-reflect the third time you catch yourself typing the same correction into Claude Code. It's the pragmatic take on agent memory: no vector DB, no service — hooks queue corrections, you review, markdown files get smarter, and the AGENTS.md sync means Codex/Cursor/Aider benefit too. The /reflect-skills pattern-mining is the sleeper feature: 15 similar requests become one command. When NOT: if you expect actual memory infrastructure (semantic recall, knowledge graphs) — this is disciplined note-taking with AI triage, personal-scale by design. Everything lands via human review, which is a feature, not friction.