Back to browse
GitHub Repository

Open-source platform layer for AI agents in production

187 starsPython

Kitaru – Open-source infrastructure for async agents

by strickvl·Mar 25, 2026·2 points·1 comment

AI Analysis

●●SolidSolve My ProblemNiche Gem

Two decorators add crash recovery when LangGraph requires full rewrites.

Strengths
  • Python-native approach avoids graph DSL complexity that frameworks like LangGraph impose.
  • Checkpoint-based replay recovers from step 6 instead of restarting entire agent runs.
  • Built-in dashboard ships free with server for cost tracking and human approval gates.
Weaknesses
  • Agent orchestration is crowded with LangGraph, CrewAI, and Temporal already established.
  • Built on ZenML which adds dependency overhead for teams not already using it.
Category
Target Audience

AI/ML engineers building production agent workflows

Similar To

LangGraph · Temporal · CrewAI

Similar Projects

AI/ML●●●Banger

Agent-recall-AI – Auto-save for AI agents that die mid-task

Auto-save for AI agents that survives context limits without changing your code.

Solve My ProblemZero to One
SrinathSankara
221mo ago
AI/ML●●Solid

AgentForge – Multi-LLM Orchestrator in 15KB of Python

AgentForge compresses common production patterns—token-aware rate limiting (token-bucket), retry+exponential backoff, prompt templates and cost tracking—into a tiny async core and lets you flip providers with one parameter. The multi-agent mesh and ReAct loop bits are the most interesting engineering bets here, and the repo includes benchmarks and a Streamlit demo, but it lives in a crowded space next to LangChain and similar toolkits so real differentiation will come from adoption and edge-case robustness.

Niche GemShip It
chunktort
213mo ago