AgentIndex icon
AgentIndex
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Submit Tool
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Home/
Dev Tooling/
Agently
Agently logo

Agently

Active·★ 1.7k·Apache-2.0·Updated 2026-10-13
★ Essential★ Trending

Agently 4 is a Python framework for building GenAI applications, installed with `pip install -U agently` and used with `from agently import Agently`. Its stated aim is to give GenAI application engineers the best developer experience by pulling LLM uncertainty back inside an engineering boundary. The README abstracts away varying model parameters, output formatting and the communication between engineering modules and GenAI logic, while leaving business logic to you. Its main idea is contract-first structured output: define a schema with `output()`, enforce critical fields with `ensure_keys` (including wildcard paths for list items) and let the framework parse and repair the result, without relying on provider-specific JSON-schema switches.

Models are configured through `OpenAICompatible` settings (base URL, model, auth), so local, hosted and proxy providers share one interface, with options such as `full_url` and custom auth headers. The README also covers tool planning with traceability, retries for missing fields and a path from demo to production, with examples under `examples/step_by_step/` including an auto-loop FastAPI service (SSE, WebSocket, POST, Docker-ready). Version 3 code lives on the `v3-final` branch. It is Apache-2.0 licensed with a docs site and English and Chinese introductions.

This write-up is based on the project's README and public repository data. We have not hand-tested the tool. Data as of 2026-10-18.

License
Apache-2.0
Latest release
v4.1.4.10 · 2026-10-13
Last commit
2026-10-13
Contributors
30
Forks
183
Open issues and PRs
16
First published
2023-06-30

Source: GitHub, npm and PyPI public APIs.

#GenAI#Python#LLM Orchestration#RAG#AI Framework#Coding#Data Analysis
$ Install
$ pip install -U agently
↗ Visit site★ GitHub
01

Features

01Structured and Streamed Output Control for LLMs
02Provider Compatibility (Local / Hosted / Proxy)
03Output Reliability (ensure_keys + retries)
04Framework-native Tooling with Traceability
05Workflow Orchestration (TriggerFlow)
02

Why choose it

+Contract-first structured output with `ensure_keys` and automatic repair keeps pipelines from breaking on missing fields
+One `OpenAICompatible` interface for local, hosted and proxy model providers
+Step-by-step examples, including a Docker-ready FastAPI service with SSE and WebSocket
+Provider-agnostic: does not depend on provider-specific JSON-schema modes
03

Trade-offs

!Version 4 is a rewrite; v3 code and docs are on a separate branch, so older tutorials may not apply
!The README describes goals and features more than showing benchmarks of output reliability
!Python only
!A smaller ecosystem than the biggest agent frameworks, so fewer community examples
04

Maintenance check

ActiveChecked: 2026-10-18
Last commit
2026-10-13
Commits, last 90 days
100+
Releases, last 90 days
6
Latest release
v4.1.4.10 (2026-10-13)
Open issues
16
Recent issues with at least one comment
10/12
Commits per week, last 12 weeks
Commits per week, last 12 weeks: 5, 3, 29, 15, 38, 40, 7, 13, 14, 0, 7, 0

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

  • #342 Consolidate sandbox provider contributions #333–#337 / 收敛沙箱 Provider 贡献10 comments · 2026-07-31
  • #324 Should local sandbox capabilities use system adaptation? 本地沙箱能力是否应该使用系统适配?7 comments · 2026-07-15
  • #255 建议agent 支持skill5 comments · 2026-03-29
  • #287 IndexError: list index out of range in response_adapter.py:164 when streaming API sends final chunk without choices5 comments · 2026-06-06
  • #359 Provider suggestion: AnyLLM gateway — one key for the full Chinese model pool (DeepSeek, Qwen, GLM, Kimi, MiniMax, Doubao, ERNIE)2 comments · 2026-08-18

Issue titles are quoted from GitHub. Open the link to check whether a problem still applies to the version you use.

05

Compatibility

OpenAI-Compatible APIs
Native
Verified via docs
Ollama
Supported
Verified via docs
DeepSeek
Supported
Verified via docs
Qwen
Supported
Verified via docs
ChromaDB
Integration
Verified via docs
06

Quick start

1
$ pip install -U agently
07

Use cases

↳Building robust GenAI applications from demo to production.
↳Developing real-time interactive AI companions or chatbots with mixed structured/unstructured outputs.
↳Implementing enterprise-grade RAG systems with traceable and defensible answers.
08

Alternatives

⚡Top VS:
VSagents-towards-production★21.7k→VSMicrosoft AutoGen★61.5k→VSSkill_Seekers★15.2k→VS1Panel★37.2k→
agents-towards-production logo
agents-towards-production★ 21.7k
This repository delivers end-to-end, code-first tutorials covering every layer of production-grade GenAI agents, guiding you from spark to scale with proven patterns and reusable blueprints for real-world launches.
VSCompare→
Microsoft AutoGen logo
Microsoft AutoGen★ 61.5k
A framework that enables the development of LLM applications using multiple agents that can converse with each other to solve tasks.
VSCompare→
Skill_Seekers logo
Skill_Seekers★ 15.2k
Convert documentation websites, GitHub repositories, and PDFs into Claude AI skills with automatic conflict detection
VSCompare→
1Panel logo
1Panel★ 37.2k
🔥 1Panel provides an intuitive web interface and MCP Server to manage websites, files, containers, databases, and LLMs on a Linux server.
VSCompare→
fastapi_mcp logo
fastapi_mcp★ 12.0k
Expose your FastAPI endpoints as Model Context Protocol (MCP) tools, with Auth!
VSCompare→
arcade-mcp logo
arcade-mcp★ 1.1k
The best way to create, deploy, and share MCP Servers
VSCompare→
GPT Researcher logo
GPT Researcher★ 30.2k
An autonomous agent that conducts deep research on any data using any LLM provider, producing detailed reports with citations from web and local sources.
VSCompare→
dagster logo
dagster★ 16.3k
An orchestration platform for the development, production, and observation of data assets.
VSCompare→
See all alternatives →

Comments

Log in to leave a comment

No comments yet. Be the first!

On this page
01Features02Why choose it03Trade-offs04Maintenance check05Compatibility06Quick start07Use cases08Alternatives
AgentEra /
Agently
↗

Python framework for GenAI apps with contract-first structured output

1.7k183Apache-2.0
Last commit1w ago
StatusActive
CategoryDev Tooling
Contributors30
Latest releasev4.1.4.10
Links
Documentation↗Discussion↗Issues↗Releases↗
Cloud Infrastructure
Ad

Deploy on DigitalOcean

Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.

Claim $200 Free Credit
© 2026 AgentIndex.app|Built by a 10-year iOS Developer.
Best by use caseAboutContactAdvertisePrivacy PolicyTerms of UseQYSGitHubBuy me a coffee ☕

Browse by Category

MCP ServersCode AssistantWorkflow AutomationRAG / Knowledge BaseMulti-AgentBrowser AutomationLLM InfraDev ToolingObservability

Not affiliated with Anthropic, OpenAI or Microsoft.