Search
“Python”
Showing 25–48 of 75 for “Python”
- 0.713score
AgenticSeek
Fosowl
Fully local, voice-enabled assistant that browses the web, writes code and plans tasks without cloud services
AgentAFreshness: A★ 27.5K - 0.475score
agentok
lyuai
Apache-2.0 drag-and-drop studio for AG2 multi-agent apps that generates self-contained Python code.
BuilderCFreshness: C★ 423 - 0.651score
mini-agi
muellerberndt
Minimal Python autonomous agent for GPT-3.5 and GPT-4 with web search, memory and a critic option.
AgentAFreshness: A★ 2.9K - 0.879score
Crawl4AI
Crawl4AI
Open-source web crawler that turns pages into LLM-ready Markdown, with an optional hosted cloud API.
InfrastructureAFreshness: A★ 86.2Kscraping - 0.853score
Hindsight
Vectorize
Agent memory system that helps agents learn over time through retain, recall and reflect operations.
InfrastructureAFreshness: A★ 53.4Kmemory - 0.851score
Faiss
Meta
Library for efficient similarity search and clustering of dense vectors, with optional GPU support.
InfrastructureAFreshness: A★ 41.2Kvector db - 0.848score
LightRAG
HKU Data Intelligence Lab
Simple and fast retrieval-augmented generation library with several chunking strategies and storage backends.
InfrastructureAFreshness: A★ 40.3Kdata - 0.834score
Stagehand
Browserbase
Open-source SDK for browser agents that combines natural-language act, extract and observe with Playwright-style control.
InfrastructureAFreshness: A★ 25.8K↓ 996K/wkbrowser - 0.581score
Giskard
Giskard
Open-source Python library for evals, red teaming and test generation for agentic systems
Observability toolAFreshness: Aevals - 0.814score
OpenLLMetry
Traceloop (ServiceNow)
Open-source observability for LLM applications, built on OpenTelemetry
Observability toolAFreshness: A★ 7.5Ktracing - 0.567score
eva
usepr
Single-file Python agent for shell and ops work that runs against any OpenAI-compatible model, with per-directory sessions.
AgentAFreshness: A★ 425 - 0.804score
Memori
Memori Labs
Memory built from what agents do, not only what they say, so later runs can avoid repeated failures.
InfrastructureAFreshness: A★ 17.1Kmemory - 0.801score
E2B
E2B
Open-source infrastructure that runs AI-generated code in isolated cloud sandboxes.
InfrastructureAFreshness: A★ 14.5Ksandbox - 0.795score
OpenSandbox
OpenSandbox (Alibaba)
Open-source sandbox platform that runs AI agent workloads in isolated environments on your own infrastructure.
InfrastructureAFreshness: A★ 16.1Ksandbox - 0.784score
CocoIndex
CocoIndex
Continuously fresh context for AI agents, with only changed data reprocessed.
InfrastructureAFreshness: A★ 11.7Kdata - 0.540score
MLE-agent
MLSysOps
Python command-line pairing agent for ML engineers that builds baselines, works Kaggle-style tasks and writes weekly reports.
AgentCFreshness: C★ 1.6K - 0.777score
Hatchet
Hatchet
Orchestration platform for AI agents, background tasks and durable workflows.
InfrastructureAFreshness: A★ 8.2Kdurable execution - 0.771score
Judgment Labs
Judgment Labs
Continuous-improvement stack for agents: monitor behavior, detect failures and validate fixes
Observability toolAFreshness: A★ 1.1K↓ 77.7K/wktracing - 0.767score
Microsandbox
Super Rad Company
Open-source, local microVM sandboxes for untrusted workloads, with an embeddable SDK and an MCP server.
InfrastructureAFreshness: A★ 8.8Ksandbox - 0.728score
MemMachine
MemVerge
Open-source long-term memory layer for AI agents with episodic and profile memory.
InfrastructureAFreshness: A★ 3.1Kmemory - 0.715score
LangMem
LangChain
Library that lets LangGraph agents extract, consolidate and search their own long-term memory.
InfrastructureAFreshness: A★ 1.7Kmemory - 0.644score
PaperQA2
FutureHouse
Retrieval augmented generation package that answers questions from scientific papers and documents with citations.
AgentBFreshness: B★ 9.5K↓ 30.7K/wk - 0.702score
WrenAI
Canner
Open-source generative BI engine that gives AI agents a governed semantic layer for correct SQL and shareable dashboards.
AgentAFreshness: A★ 18K - 0.697score
AgentOps
AgentOps
Observability and dev-tool platform for building, evaluating and monitoring AI agents
Observability toolCFreshness: C★ 5.9Ktracing