deepansh-saxena/DuraLang
Make stochastic AI systems durable with one decorator
This helps developers build AI agents that are resilient to failures like network timeouts or system crashes. It takes existing LangChain agent code and makes every individual LLM or tool call automatically recoverable and retryable. This ensures that long-running AI agent tasks, which might involve many steps, don't lose all progress if an intermediate step fails. It's designed for Python developers creating complex, multi-step AI agents using LangChain.
Available on PyPI.
Use this if you are developing LangChain-based AI agents and need them to reliably complete tasks without failing due to transient errors or system outages, automatically resuming from the last successful step.
Not ideal if your AI agent workflows are simple, deterministic pipelines that don't involve unpredictable LLM-driven decision making or long-running operations prone to external failures.
Stars
8
Forks
—
Language
Python
License
MIT
Category
Last pushed
Apr 01, 2026
Commits (30d)
0
Dependencies
5
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/deepansh-saxena/DuraLang"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
JackChen-me/open-multi-agent
TypeScript multi-agent framework — one runTeam() call from goal to result. Auto task...
rohitg00/pro-workflow
Claude Code learns from your corrections — self-correcting memory that compounds over 50+...
Armur-Ai/Pentest-Swarm-AI
Autonomous penetration testing using a swarm of AI agents. Orchestrates recon, classification,...
aiperceivable/apflow
**AI-Perceivable Distributed Orchestration** apflow is a distributed task orchestration engine...
ProxySoul/soulforge
Graph-powered code intelligence, multi-agent coding with codebase-aware AI. Good bye grep & pray