# AgentEra/Agently

[GenAI Application Development Framework]  🚀 Build GenAI application quick and easy 💬 Easy to interact with GenAI agent in code using structure data and chained-calls syntax 🧩 Use Event-Driven Flow *TriggerFlow* to manage complex GenAI working logic 🔀 Switch to any model without rewrite application code

Repository: https://github.com/AgentEra/Agently
Canonical: https://ross.abutalabs.com/products/agently
Homepage: http://agently.tech
Language: Python
License: Apache-2.0
License Family: permissive
Topics: agent, agent-framework, python, framework, agent-based-framework, chatglm, ernie, google-gemini, gpt, llm-agent, llm-application, llm-apps, llm-framework, llmops, llms, gemini, claude, minimax, deepseek
Last push: 2026-08-26T09:17:52+00:00

## Health v2 (maintenance only)
Score: 94/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 99, release rhythm 95, longevity 82
- inputs: {"age_days": 1160, "days_push": 7, "days_rel": 33, "gap_med": 10.0, "n_releases_24m": 41}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1644, forks 182 (observed 2026-08-28T04:05:16.143218+00:00)

## What it is
Agently is a Python framework for building production-grade GenAI applications with structured outputs, observable actions, MCP/tool integration, and event-driven TriggerFlow workflow orchestration. It abstracts model providers behind protocol-compatible plugins (OpenAI, Anthropic, etc.) so application code can switch models via configuration without rewrites.

## Use cases
- build an AI agent backend that returns structured JSON fields
- switch LLM providers without rewriting application code
- orchestrate multi-step GenAI workflows with branching and pause/resume
- stream structured output fields to a frontend as they generate
- add tool calling, MCP servers, and sandboxed code execution to an agent
- build a RAG chatbot over a knowledge base
- expose an agent as an HTTP API service
- route support tickets with structured classification

## When to choose
- you need stable, validated structured outputs from LLMs in Python
- you want model-provider portability via config-only switching
- you need persistent, event-driven workflows around agent calls
- you want built-in observability, action logs, and execution evidence for production AI services

## When to avoid
- you only need a single one-off LLM call with no structure or tooling
- your stack is not Python
- you want a minimal thin wrapper rather than an opinionated framework with its own orchestration layer

## Facets
- artifact type: framework
- maturity: active
- function: agent-framework, llm-inference, rag, workflow-automation, mcp, chatbot, web-framework, sdk
- domain: artificial-intelligence, large-language-models, developer-tools, backend
- platform: python, cross-platform, self-hosted
- tags: structured-output, triggerflow, schema-as-prompt, model-agnostic, event-driven, llmops, fastapi-integration, sandboxed-code-execution, streaming, ai-agents, retrieval-augmented-generation, automation, docker

## Member repositories
- AgentEra/Agently (main) score 94

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:16.143218+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T03:45:47.245826+00:00, confidence not recorded.
  - readme: https://github.com/AgentEra/Agently (fetched 2026-08-28T04:05:16.143218+00:00, sha 9947949f67c7)
  - homepage: http://agently.tech (fetched 2026-08-29T11:19:29.615794+00:00, sha 8a58db9d34a7)
  - site_page: https://agently.tech/docs/reference/capability-map.html (fetched 2026-08-29T11:19:29.629840+00:00, sha b73efbdce9fd)
  - site_page: https://agently.tech/docs/start/project-framework.html (fetched 2026-08-29T11:19:29.631864+00:00, sha 9c3cb231e4fa)
  - site_page: https://agently.tech/docs/playbooks/overview.html (fetched 2026-08-29T11:19:29.633566+00:00, sha 0d19927f46dd)
  - site_page: https://agently.tech/docs (fetched 2026-08-29T11:19:29.635284+00:00, sha 13e6b1fed08e)
  - site_page: https://agently.tech/docs/case-studies/overview.html (fetched 2026-08-29T11:19:29.636998+00:00, sha caf5701f3b5c)
  - site_page: https://agently.tech/docs/start/quickstart.html (fetched 2026-08-29T11:19:29.638570+00:00, sha 9d0c9065c97b)
  - site_page: https://agently.tech/docs/requests/output-control.html (fetched 2026-08-29T11:19:29.640191+00:00, sha 3999b9a701ad)
  - site_page: https://agently.tech/docs/actions/overview.html (fetched 2026-08-29T11:19:29.642257+00:00, sha 8d2c47b86eae)
- Data as of 2026-08-30T08:39:29.467469+00:00.