Skip to content
#

crash-recovery

Here are 222 public repositories matching this topic...

CONTINUUM: Verifiable semantic recovery for long-running AI agents. Semantic checkpoints (not conversation dumps), an idempotent action ledger that refuses duplicate side effects, and a hash-chained tamper-evident event log, all exposed as a deny-by-default MCP server. Framework-agnostic, Python 3.11+.

  • Updated Oct 12, 2026
  • Python

Give an API-only agent real continuity: live on Telegram and your terminal in one session, with built-in layered memory (auto-folding + day/week cards) and a local memory console. The astronaut's tether — the line that must not break.

  • Updated Aug 10, 2026
  • JavaScript

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.

  • Updated Sep 17, 2026
  • TypeScript

Add this topic to your repo

To associate your repository with the crash-recovery topic, visit your repo's landing page and select "manage topics."

Learn more