The open-source memory and observability layer for AI agents — persistent memory, loop detection, hash-chained audit trails, and a live dashboard, automatic on pip install.
-
Updated
Jul 15, 2026 - Python
The open-source memory and observability layer for AI agents — persistent memory, loop detection, hash-chained audit trails, and a live dashboard, automatic on pip install.
DSH crash-rescue plugin: undo config & plugin-code changes, secret-safe snapshots, one-click SAFE MODE, plus offline CLI/GUI that work even when DSH won't boot.
Open-source local policy, recovery, and audit layer for explicit Codex execution.
tmux-resurrect for herdr — snapshot workspaces, tabs, panes, cwd, running programs and agents, and restore them after a crash or reboot.
Telegram 媒体下载/转发/监听工具 — 任务持久化 + 崩溃恢复 + Pending 队列 + FLOOD_WAIT 非阻塞处理 + 现代 WebUI
Open-source plugin-based notification orchestration engine for developers who value control
Redis-inspired in-memory key–value database in C with WAL, crash recovery, TTL, AOF rewrite, REPL, and TCP server. Built to understand real database internals.
oh-my-fable — Fable 5's way of working a long task (plan first, self-correct, never lose the thread), as a model-agnostic agent harness. The run lives in one serializable RunContext, checkpointed every step, so a crash is a pause. Zero deps, deterministically testable.
Local-first recovery tool for interrupted and damaged OpenAI Codex sessions
A lightweight process supervisor for Windows desktop apps. Auto-restarts your apps when they crash.
Stateless CLI giving AI coding agents persistent identity, a typed lifecycle, and crash-recovery. Self-hostable, AGPL-3.0.
A fully functional Raft-based distributed ans Sharded key-value store in Go, supporting leader election, log replication, snapshotting, and crash recovery — built for MIT 6.824 lab assignments to demonstrate consensus, fault tolerance, and high availability.
LokiVector - The AI-Era Embedded Database: Document Store + Vector Search with Crash-Tested Durability. MIT Licensed Community Edition.
A C++23 LSM-tree key-value store with crash recovery and a gRPC API supporting point operations and server-streaming range scans.
Zero-cost, crash-proof LLM pipeline orchestrator. Features disk-based checkpointing, free-tier routing, and structured output. (LangGraph / CrewAI alternative)
Crash-safe auto-updates for Go applications — versioned deployments with automatic rollback when the new version fails.
Asynchronous event-driven job processing queue in Go with durable SQLite persistence, at-least-once execution, visibility timeouts, retries/DLQ, and crash recovery.
A lightweight Python package that Keep your bots alive with automatic restarts, heartbeat monitoring, and a built-in status dashboard.
Autonomous crash recovery for your terminal: wrap a command; on crash, headless Claude Code diagnoses, tests, patches on a branch, and writes a post-mortem.
Add a description, image, and links to the crash-recovery topic page so that developers can more easily learn about it.
To associate your repository with the crash-recovery topic, visit your repo's landing page and select "manage topics."