LightAgent
Active·★ 1.2k·Apache-2.0·Updated 2026-11-15
LightAgent is a modular Python framework for OpenAI-compatible agents. It includes tools and skills, optional memory, routing and workflow components, plus an opt-in durable runtime with policy and approvals.
#agent-framework#agent-hooks#agents#ai-agent#lifecycle-hooks#llm#mcp#multi-agent
01
Features
01Connects tools and skills to OpenAI-compatible models.
02LightSwarm, LightFlow and LightDAG address different coordination patterns.
03Optional integrations cover memory, MCP and tracing.
02
Why choose it
+
+
+
+
03
Trade-offs
!
!
!
!
04
Maintenance check
ActiveChecked: 2026-11-18
- Last commit
- 2026-11-15
- Commits, last 90 days
- 68
- Releases, last 90 days
- 4
- Latest release
- v1.0.0 (2026-11-15)
- Open issues
- 4
- Recent issues with at least one comment
- 4/4
Commits per week, last 12 weeks
Oldest week on the left; the latest four weeks are orange. Source: GitHub commit activity.
Status rule: archived on GitHub = Archived; last commit within 90 days = Active; 91 to 365 days = Slowing; older = Stale. All figures come from the GitHub API on the date shown.
Most discussed open issues
- #39 Responsible Disclosure: High-Severity Vulnerability in Shared Graph-Based Agent Memory22 comments · 2026-05-12
- #100 Responsible Disclosure: Sandbox Escape in the Built-in Python Executor6 comments · 2026-09-02
Issue titles are quoted from GitHub. Open the link to check whether a problem still applies to the version you use.
05
Compatibility
python
Python package; optional extras install separate integrations
Verified via docs
openai-api
OpenAI-compatible model endpoint required
Verified via docs
06
Quick start
1
$ pip install lightagent
07
Use cases
↳Build a tool-using Python agent.
↳Route requests among several agents.
↳Organize a repeatable workflow with explicit steps.
08
Alternatives
Sage★ 1.2k
An RSI Agent Harness for running, evaluating, and evolving agents—with tools, skills, MCP, stateful execution, and multi-agent workflows.
OpenExecutive★ 5.8k
AI-powered virtual executive team — a single coherent executive persona backed by 8 specialist agents (FastAPI + Next.js).
trpc-agent-go★ 1.9k
A Go framework for building production agent systems with graph workflows, tools, memory, A2A, AG-UI, MCP, evaluation, and observability.
deer-flow★ 85.5k
DeerFlow is a community-driven Deep Research framework, combining language models with tools like web search, crawling, and Python execution, while contributing back to the open-source community.
ggui★ 44
The universal interface layer between AI agents and humans. Generate rich UIs on demand via MCP.
Comments
Log in to leave a comment
No comments yet. Be the first!