l123-harness
by reatcat · reatcat/l123-harness
★ 4 Stars
⑂ 0 Forks
Updated: Aug 22, 2026
MIT
Shell
Original language: English
About
Three-tier agent memory harness: L1 always-on CLAUDE.md, L2 index, L3 detail skeleton with templates, a gate that blocks writes to protected files without a one-time approval token, zero-judgement event logging, weekly distillation, and a TDD execution-loop skill.
Similar plugins
by zilliztech
A persistent, unified memory layer for all your AI agents (e.g. Claude Code, Codex, DSH), backed by Markdown and Milvus.
★ 2.6k
↓ 306/wk
MIT
Python
Sep 12, 2026
dsh plugin --profile web add @zilliz/memsearch-dshby mnemon-dev
LLM-supervised persistent memory for AI agents — graph-based recall, cross-session knowledge, single binary. Works with DeepSeek Harness, Claude Code, OpenClaw, and any agent runtime.
★ 574
Apache-2.0
Go
Sep 12, 2026
dsh plugin --profile web add @mnemon-dev/dsh-mnemonby 398894496-arch
Second brain for coding agents. Seal the day, distill into Obsidian, hit that page tomorrow. Cursor, Codex, Claude Code, DeepSeek Harness.
★ 38
MIT
Python
Sep 12, 2026
dsh plugin --profile web add dsh-krouterPersistent memory for DeepSeek Harness: memory read/write/retrieve tools, per-turn auto-recording, project-scoped recall injection and a management UI, with non-destructive Claude Code memory import.
★ 0
↓ 538/wk
dsh plugin --profile web add dsh-memoryby flymysql
DeepSeek Harness 跨会话记忆库：memory_remember/recall/forget 三个工具 + 系统提示注入，agent 持久化记忆
★ 6
↓ 211/wk
MIT
JavaScript
Aug 14, 2026
dsh plugin --profile web add dsh-memory-vaultby tinqiao-oss
A portable memory protocol for AI agents — load it as standing rules; a curation discipline + reference spec + optional cap hook.
★ 190
↓ 158/wk
MIT
Python
Sep 8, 2026
dsh plugin --profile web add dsh-engramory