Rollback Python Packages

bilinc

Hosted memory for AI agents: commit, recall, revise, snapshot and roll back agent state with provenance. Python SDK, CLI and MCP server. Free, no card required.

pytest-mrt

Catch database migration rollback failures before they reach production

task-checkpoint-mcp

MCP server adding checkpoint and resume to long agent tasks: roll back to any step, pick the work up in a new session, hand off to another machine. Works with Claude Code, Codex and other MCP clients. Pure Python stdlib, zero dependencies, never touches your git history.

revoco

Undo for AI agent actions. Plans the rollback before the action runs, proves it still works, and rolls back a compromised grant's whole blast radius in one call.

workspace-metabolism

Govern what Claude Code, Codex, Aider and OpenClaw leave in your workspace: one JSON policy file, audit, recyclable clean, rollback, hash-chained audit trail.

opshield

AI agent safety platform: rollback, cost control, circuit breakers, tracing, compliance, and chaos testing. Zero dependencies.

stepback

Git time-travel for AI coding agents. Checkpoint and rewind Claude Code, Codex, aider, or any command—without touching HEAD, staging, or your branch.

self-improving-loop

Rollback-first reliability layer for AI agents: trace failures, apply guarded changes, and rollback on regression.

super-skill-cli

Git-backed version control, rollback, and provenance for your Claude Code & Codex Agent Skills — a safety-gated skill package manager (CLI + plugin).

snapm

Snapshot Manager

runsheet

Type-safe, composable business logic pipelines for Python

triggon

Label-based triggers, deferred execution, and runtime value switching for Python.

vmigration-helper

Helpers for working with Django migrations

unwind-mcp

Deterministic security engine for AI agents. See, block, rewind, prove.

anchorai

The official SDKs for Anchor API.

fs-transaction

Atomic filesystem operations for safe batch processing.

vpmx

Resumable, trackable script orchestration for VPS and local environments. Security scanning, rollback, crash recovery.

model-action-protocol

MAP (Model Action Protocol) — Cryptographic provenance, self-healing critic, and state rollback for autonomous AI agents. 2.5k lines of TypeScript, 60+ tests, MIT.

autodeploydocker

A new package that simplifies the deployment of Docker and Docker Compose applications to servers without requiring configuration changes or causing downtime. It automates the process, making it acces

larzmigrate

Schema migrations for SQL (any DB-API) and larzdb: ordered up/down, rollback, checksum drift detection. Pure Python, zero dependencies.

pherix

Transactional resource runtime for AI agents — undo the reversible, gate the irreversible, against your backend's own state.

safeloop

Transactional agent runtime for evidence, verification, rollback, and recoverability.

fable-harness

Project-local agent harness skill for traceable AI workflows