DISCOVER THE FUTURE OF AI AGENTSarrow_forward

RexCLI

calendar_todayAdded Apr 23, 2026
categoryAgent & Tooling
codeOpen Source
Node.jsWorkflow AutomationMulti-Agent SystemModel Context ProtocolPlaywrightAI AgentsCLIAgent & ToolingDeveloper Tools & CodingKnowledge Management, Retrieval & RAGProtocol, API & Integration

A local-first AI memory system and orchestration layer for existing coding agents like Codex CLI, Claude Code, and Gemini CLI

RexCLI (CLI command aios) is a local-first AI agent bootstrap that provides three shared infrastructures for coding agents like Codex CLI, Claude Code, Gemini CLI, and OpenCode without replacing their model invocation capabilities: a cross-CLI persistent memory system (ContextDB) based on better-sqlite3, unified browser automation via Playwright MCP (browser_* toolset with CDP support), and an automatic Privacy Guard for sensitive file sanitization.

Shared Infrastructure#

  • ContextDB: Cross-CLI filesystem persistent storage supporting session / event / checkpoint / context:pack subcommands, built on better-sqlite3 (requires Node ABI match)
  • Unified Browser Automation: Playwright MCP Server provides standardized browser_* toolset with CDP (Chrome DevTools Protocol) connection support
  • Privacy Guard: Automatic sanitization before reading config/key files, config stored at ~/.rexcil/privacy-guard.json, optional local Ollama (qwen3.5:4b) path

Operator Toolbox#

  • Quality Gate: aios quality-gate full / pre-pr --profile strict for repo health + ContextDB regression guards
  • Learn-Eval: aios learn-eval --limit 10 converts checkpoint telemetry into actionable insights
  • Orchestrate: Blueprint orchestration + local scheduling skeleton + token-free dry-run; --dispatch local --execute live for actual model calls
  • Team Runtime: aios team 3:codex "Ship X" for multi-agent parallel collaboration with dry-run / resume / retry-blocked support
  • HUD: aios hud --provider codex --watch --preset full for session visibility
  • Snapshot Rollback: Pre-mutation snapshots + post-incident rollback for recovery

Skills System#

Standardized skill source tree supporting global and project scopes. Core skill set includes skill-constraints, aios-project-system, aios-long-running-harness, contextdb-autopilot, etc., with interactive install/uninstall via TUI SkillPickerScreen.

Architecture & Call Chain#

User → codex/claude/gemini
     → (zsh wrapper: contextdb-shell.zsh)
     → contextdb-shell-bridge.mjs
     → ctx-agent.mjs
        → contextdb CLI (init/session/event/checkpoint/pack)
        → start native codex/claude/gemini (with context packet)
     → mcp-server/browser_* (optional browser automation)

Native CLI calls are transparently intercepted via a zsh wrapper, bridged through contextdb-shell-bridge.mjs, and processed by ctx-agent.mjs for ContextDB session initialization and context packing before launching the native CLI with a context packet.

Upstream Agent Integration#

  • Codex CLI: Deep adaptation for v0.114+ structured exec outputs (--output-schema + --output-last-message + stdin), fallback to stdout parsing for older versions
  • Claude Code / Gemini CLI: Unified access via Shell Wrapper
  • OpenCode: Documented support

Installation & Prerequisites#

Runtime strictly requires Node.js 22 LTS ("engines": { "node": ">=22 <23" }), supporting macOS, Linux, and Windows (PowerShell).

macOS / Linux one-line install:

curl -fsSL https://github.com/rexleimo/rex-cli/releases/latest/download/aios-install.sh | bash
source ~/.zshrc
aios

Windows PowerShell one-line install:

irm https://github.com/rexleimo/rex-cli/releases/latest/download/aios-install.ps1 | iex
. $PROFILE
aios

Key Environment Variables#

VariableDescription
AIOS_SUBAGENT_CLIENTSub-agent client: codex-cli / claude-code / gemini-cli
AIOS_SUBAGENT_CONCURRENCYConcurrent sub-agent count
AIOS_EXECUTE_LIVESet to 1 to enable live execution with actual model calls
AIOS_SUBAGENT_PRE_MUTATION_SNAPSHOTSet to 1 to create file snapshots before live execution
CTXDB_WRAP_MODErepo-only (default) / opt-in (requires .contextdb-enable marker)

RL Experiment Module#

Repository contains experiments/rl-shell-v1 providing RL (reinforcement learning) experiment infrastructure with benchmark, training (phase 2A), evaluation (phase 2B), and campaign scripts. Production readiness status is unclear.

Unconfirmed Information#

  • No LICENSE file found in repository root; open-source license type cannot be confirmed
  • No associated Hugging Face model page or academic paper citations found
  • Privacy Guard local Ollama path's specific model capabilities are unverified

Related Projects

View All arrow_forward

STAY UPDATED

Get the latest AI tools and trends delivered straight to your inbox. No spam, just intelligence.

rocket_launch