Agent skill
memex-cli
Execute AI-powered command-line tasks with memory, replay, and resume capabilities using memex-cli. Use when (1) Running AI backend tasks (codex, claude, gemini), (2) Replaying recorded events from JSONL files, (3) Resuming interrupted runs by run_id, (4) Executing prompts with streaming output in jsonl or text format.
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/development/memex-cli
SKILL.md
Memex CLI
A CLI wrapper for AI backends with built-in memory, replay, and resume support.
Core Commands
Run a Task
memex-cli run \
--backend <backend> \
--prompt "<prompt>" \
--stream-format <format>
Parameters:
--backend: AI backend (codex,claude,gemini)--prompt: Task prompt--stream-format: Output format (jsonlortext)--model: Model name (optional, for codex backend)--model-provider: Model provider (optional, for codex backend)
Replay Events
memex-cli replay --events ./run.events.jsonl --format text
Replays a previously recorded run from its event log.
Resume a Run
memex-cli resume \
--run-id <RUN_ID> \
--backend <backend> \
--prompt "<prompt>" \
--stream-format <format>
Continues a previous run using its run_id.
Backend Examples
Codex
memex-cli run --backend "codex" --model "deepseek-reasoner" --model-provider "aduib_ai" --prompt "任务描述" --stream-format "jsonl"
Claude
memex-cli run --backend "claude" --prompt "任务描述" --stream-format "jsonl"
Gemini
memex-cli run --backend "gemini" --prompt "任务描述" --stream-format "jsonl"
Output
Each run generates run.events.jsonl for auditing and replay.
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
majiayu000/claude-skill-registry
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
majiayu000/claude-skill-registry
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
majiayu000/claude-skill-registry
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
majiayu000/claude-skill-registry
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
majiayu000/claude-skill-registry
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
majiayu000/claude-skill-registry
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?