by kargarisaac · Codex Skill · ★ 97
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
Compiles AI agent traces and truns them into reusable context.
| Stars | 97 |
| Forks | 6 |
| Language | Python |
| Category | Codex Skill |
| Quality Score | 47.3901976968222/100 |
| Last Updated | 2026-09-16 |
| Created | 2026-02-23 |
| Platforms | claude-code, codex, python |
| Est. Tokens | ~13k |
These tools work well together with lerim for enhanced workflows:
Looking for a lerim alternative? If you're comparing lerim with other codex skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Compiles AI agent traces and truns them into reusable context.
Compiles AI agent traces and truns them into reusable context.
Compile completed AI agent runs into reusable, cited context.
Project memory system for AI coding assistants (Claude Code, Cursor, Codex): session logs, project wiki, rules
Project memory for long-running AI work across agents, models, and sessions. Keep context, decisions, progress
Outcome-based persistent memory MCP server for Claude Code and OpenCode. Good advice promoted, bad advice demo
Explore other popular codex skill tools:
lerim is Compiles AI agent traces and truns them into reusable context.. It is categorized as a Codex Skill with 97 GitHub stars.
lerim is primarily written in Python. It covers topics such as agent-memory, ai-coding, ai-coding-agent.
You can find installation instructions and usage details in the lerim GitHub repository at github.com/kargarisaac/lerim. The project has 97 stars and 6 forks, indicating an active community.
The top alternatives to lerim on Agent Skills Hub include lerim, lerim, lerim-cli. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: