agent-memory

Featured

Use when a project's CLAUDE.md has grown past what anyone reads and you want the agent to learn durable facts from its own sessions instead — or when asking why the agent keeps re-learning the same correction, why a remembered rule is wrong, or where a memory line came from. Implements a four-tier store (L0 transcripts / L1 candidates / L2 project context / L3 stable persona) where promotion is earned by recurrence across sessions and days, never by one confident statement, and nothing reaches a committed file without a human adopting it.

AI & Automation 24,927 stars 3509 forks Updated today MIT

Install

View on GitHub

Quality Score: 99/100

Stars 20%
100
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
50
License 10%
100
Description 5%
100

Skill Content

# Agent Memory — promotion is earned, not asserted > **Portability:** stdlib only. No database, no embeddings, no network, no LLM calls. ## The problem A project's `CLAUDE.md` is a memory system with one tier and no eviction: every durable fact and every passing preference land in the same always-loaded file, until the important lines are diluted by the incidental ones. Facts learned mid-session vanish at teardown unless someone writes them down. **The fix is not more storage — it is a promotion ladder.** A claim earns its way toward always-loaded context by recurring; a human confirms the last step. ## The four tiers Tiers are distinguished by **injection policy**, not storage format. | Tier | Holds | Injected | Committed | |---|---|---|---| | **L0** | raw session transcripts | never | no (already on disk) | | **L1** | candidate atoms | on relevance, at prompt time | no (gitignored) | | **L2** | this project's context | every session start | yes, after adopt | | **L3** | stable cross-project persona | always | yes, after adopt | ## The gates Nothing moves up because it sounded important. It moves up because it recurred. - **L0 → L1** — an explicit marker fires (a directive, a correction, a stated preference, a named lesson, a reproducible failure). Rule-based, high precision, deliberately low recall. - **L1 → L2** — ≥ 3 distinct sessions spanning ≥ 2 distinct calendar days. A claim stated outright needs 2 sessions; the distinct-day rule still applies. A ver...

Details

Author
alirezarezvani
Repository
alirezarezvani/claude-skills
Created
10 months ago
Last Updated
today
Language
Python
License
MIT

Integrates with

Bundled in these plugins

Similar Skills

Semantically similar based on skill content — not just same category

AI & Automation Solid

claude-memory-kit

Persistent memory for Claude Code agents with an agent-audit-ritual architecture. User only talks; the agent captures, audits, proposes promotions, and writes. Memory lives in layers — a hot cache (MEMORY.md) held under three size caps, per-session handoffs (context/handoffs/), topical knowledge articles (knowledge/concepts/), and canonical rules (.claude/rules/) — plus multi-project isolation via projects/<name>/ and an experiments/ sandbox. /close-session runs the end-of-session audit ritual. Zero external dependencies.

30 Updated 6 days ago
awrshift
AI & Automation Listed

memory-engineering

Use when an agent's memory needs to be built, audited, or maintained — the user asks to set up a memory system, complains the agent keeps forgetting or repeating mistakes, says the instruction file (CLAUDE.md/AGENTS.md) has grown bloated or contradictory, asks what should be remembered vs deleted, or says 'remember this'. Triggers: memory engineering, bootstrap a memory system, audit my memory, my agent forgets everything, CLAUDE.md is a mess, run the memory sweep, 建記憶系統, 健檢記憶, 清理記憶. Not a vector database or retrieval tool.

0 Updated 1 weeks ago
danyuchn
AI & Automation Listed

self-improving-agent

Auto-curate memory, promote recurring patterns, and extract reusable knowledge across sessions. TRIGGER when: user says "/si:", asks about memory management, pattern promotion, or wants to review accumulated learnings. DO NOT TRIGGER when: user wants general code review, documentation, or project planning.

0 Updated 3 weeks ago
DROOdotFOO