checkpointing repositories
Trending repositories tagged checkpointing, ranked by trending score. Updated daily.
-
1
shuxiachai/academic-commercialization-agent
AI multi-agent tool that turns research papers into cited commercialization and tech-transfer assessments: TRL, patent landscape, market and risks. CrewAI + FastAPI, with a reproducible benchmark.
GitHub · Python · 819 stars · 102 forks · +5 stars in 24 hours · Trending score 1.51
-
2
ThousandBirdsInc/chidori
The agent framework where every run is durable, replayable, and resumable by default.
GitHub · Rust · 1,372 stars · 63 forks · 0 stars in 24 hours · Trending score 0.48
-
3
trigora-dev/trigora
High-performance, lightweight durable execution for long-running AI agents and programs.
GitHub · Rust · 67 stars · 9 forks · +1 stars in 24 hours · Trending score 0.45
-
4
ZJU-REAL/ageval
A composable framework for reproducible evaluation of long-running agents.
GitHub · Python · 82 stars · 4 forks · 0 stars in 24 hours · Trending score 0.38
-
5
iltsarev/detach
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.
GitHub · Swift · 16 stars · 3 forks · 0 stars in 24 hours · Trending score 0.30
-
6
Under-Research-Labs/CONTINUUM
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+
GitHub · Python · 27 stars · 55 forks · 0 stars in 24 hours · Trending score 0.24
-
7
hpoenixf/open-etf-agent
Build an ETF research agent, one working module at a time. Runnable code, bilingual deep dives, and a traceable 0→1 journey.|逐模块构建 ETF 投研 Agent:可运行代码、中英双语深度解析与可追溯的 0→1 演进。
GitHub · JavaScript · 28 stars · 1 forks · 0 stars in 24 hours · Trending score 0.24
-
8
Francis1998/multi-bot-agentic
Deterministic, auditable multi-bot AI-agent orchestrator: Observe→Decide→Act loop with rationale traces, replayable SQLite event log with resume and time-travel forks, strict golden-path offline evals, OpenTelemetry GenAI trace export, MCP tool bridge, safety controls, and GPT-6.2, Claude 5.5 / Fable 5.2, Gemini 4 and Kimi K3.1 adapters.
GitHub · Python · 11 stars · 0 forks · 0 stars in 24 hours · Trending score 0.22
-
9
argonne-lcf/dlio_benchmark
An I/O benchmark for deep Learning applications
GitHub · Python · 113 stars · 64 forks · 0 stars in 24 hours · Trending score 0.15
-
10
sayiir/sayiir
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.
GitHub · Rust · 81 stars · 10 forks · −1 stars in 24 hours · Trending score 0.10
-
11
limenagent/prodagent
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
GitHub · Python · 114 stars · 29 forks · 0 stars in 24 hours · Trending score 0.00
-
12
MalganisWu/red-bean-qing-tuan
可嵌入的 TypeScript Agent Runtime —— model→tool 循环、checkpoint、interrupt 屏障,零生产依赖,可嵌进任何宿主。
GitHub · TypeScript · 95 stars · 0 forks · 0 stars in 24 hours · Trending score 0.00
-
13
ECP-VeloC/VELOC
Very-Low Overhead Checkpointing System
GitHub · C++ · 59 stars · 27 forks · −1 stars in 24 hours · Trending score -0.00