The agent framework where every run is durable, replayable, and resumable by default.
-
Updated
Sep 10, 2026 - Rust
The agent framework where every run is durable, replayable, and resumable by default.
A GPipe implementation in PyTorch
An I/O benchmark for deep Learning applications
A minimal, readable agent-framework kernel — understand how LangGraph/ADK work under the hood. 1800行代码的 agent 框架内核,理解 LangGraph/ADK 底层的工作原理
Sayiir: simple, embeddable durable workflow engine in Rust with Node.js & Python bindings. Checkpoint-based recovery, no deterministic replay. A simplified alternative to Temporal, Restate, and Airflow.
Very-Low Overhead Checkpointing System
Extending DOLFINx with checkpointing functionality
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+.
Keras wrapper that autosaves what ModelCheckpoint cannot.
Execution runtime for intelligent agents with event-sourced, recoverable task orchestration.
Run Codex and Claude Code reliably in the background on macOS—with a native dashboard, persistent tmux sessions, local checkpoints, recovery, notifications, and closed-lid support.
Git-like branching, checkpointing, and comparison for AI agent execution paths. pip install agentgit
Weavegraph rust graph/agent/node
GenPark AI Agent Skill - Transactional agent state checkpointer with deterministic snapshotting, time-travel rollback, and branch history tracking.
GenPark AI Agent Skill - Transactional agent state checkpointer with deterministic snapshotting, time-travel rollback, and branch history tracking.
A platform for running sandboxed containers
Corso web gratuito in italiano, con repository open source, per costruire da zero un modello GPT decoder-only in PyTorch in 42 lezioni con spiegazioni, matematica, codice eseguibile e snapshot progressivi.
Minimal PyTorch training framework — implement three methods, get a full training loop: composable phases, checkpointing, early stopping, metrics, and a live web dashboard.
Independent LangGraph C++ runtime for stateful AI agents and recoverable graph workflows: checkpointing, streaming, interrupts, tool calling, edge/local LLM apps. C++23 developer preview; not official LangGraph/LangChain.
To associate your repository with the checkpointing topic, visit your repo's landing page and select "manage topics."