v4.1.3

Highlights

• Promotes the 4.1.2 runtime foundation into a coherent AI application runtime for production-grade AI service backends.
• Makes one Agent turn able to connect model reasoning, Actions, remote Skills, MCP tools, Dynamic Task DAGs, process streams, structured outputs, and coding-agent guidance through one engineering path.
• Adds Agent auto-orchestration so agent.start() can route through ordinary model response, Actions, Skills Executor, or Dynamic Task when those candidates are declared.
• Turns Skills into runtime capabilities declared through agent.use_skills(...), with lazy remote discovery, on-demand materialization, MCP/script mounting, effort-aware execution, and structured diagnostics.
• Adds agent.activate_model(...) and Model Pool / Key Pool guidance for switching concrete model aliases such as ollama-qwen2.5 and deepseek-v4 without rewriting business logic.

Business Value

Agently 4.1.3 is aimed at AI services with real backend responsibilities: stable output contracts, observable tool calls, external-system boundaries, recoverable execution, and rich process streams for UIs and logs.

Typical 4.1.3 services can now express:

• business input contracts and structured output contracts
• reusable Actions and external MCP services
• remote Skills from public or private repositories
• dynamic task graphs for complex decomposition
• streamable execution objects for frontend progress and runtime evidence
• model-stage routing through configured model aliases and key pools

Example Shape

result = (
    agent
    .activate_model("ollama-qwen2.5")
    .use_actions([lookup_customer, fetch_contract, notify_owner])
    .use_skills(
        [{"source": "anthropics/skills", "subpath": "skills/docx"}],
        mode="model_decision",
    )
    .use_dynamic_task(mode="auto", max_tasks=8)
    .input({"customer_id": "C-1024", "ticket": "payment failure"})
    .output({
        "summary": (str, "business summary", True),
        "risk_level": (str, "low / medium / high", True),
        "next_actions": ([str], "recommended actions", True),
    })
    .start()
)

Documentation

• English release notes: docs/en/development/release-notes-4.1.3.md
• Chinese release notes: docs/cn/development/release-notes-4.1.3.md
• PyPI package: https://pypi.org/project/agently/4.1.3/

v4.1.2

Highlights

• Added Action Execution Environment v2 for managed runtime resources.
• Added Action-native built-in capability packages for Search, Browse, and Cmd.
• Added agent capability helpers for common execution capabilities such as Python, shell, Node.js, SQLite, and workspace access.
• Added compact action execution recall with artifact-backed full result access.
• Added companion compatibility manifests for Agently, Agently-Skills, and Agently-Devtools release alignment.

Features

Action Execution Environment

1. [ExecutionEnvironment] Added managed environment lifecycle support for Python, Bash, Node.js, Docker, Browser, SQLite, and MCP resources.
2. [ExecutionEnvironment] Added provider contracts for declaring, ensuring, health-checking, injecting, and releasing managed resources.
3. [Action] Added environment-aware action execution so executors can receive managed handles and resources without changing executor call signatures.
4. [TriggerFlow] Added support for managed execution-local resources while keeping runtime_resources as the compatibility surface.

Built-in Actions

1. [Action] Added Action-native built-in packages under agently.builtins.actions.
2. [Action] Added Search and Browse packages with Action Runtime integration.
3. [Action] Added Cmd and sandbox-oriented execution paths for local command workflows.
4. [Action] Added execution recall so instruction-heavy action outputs can be summarized in model context while full outputs remain available through artifacts.

Agent Capability Helpers

1. [Agent] Added capability helpers for common managed execution capabilities.
2. [Agent] Added desc_mode behavior for helper descriptions, supporting default, append, and override modes.
3. [Agent] Improved default helper descriptions so model-facing action guidance keeps baseline usage and safety constraints.

Updates

Runtime And Observability

1. [Runtime] Improved runtime console log routing.
2. [Observability] Preferred ObservationEvent naming while keeping legacy runtime event compatibility.
3. [EventCenter] Expanded event coverage for action and execution-environment lifecycle paths.

Compatibility

1. [Compatibility] Added version-scoped compatibility manifests under compatibility/releases/.
2. [Compatibility] Added release index metadata for current and in-development compatibility lines.
3. [Compatibility] Added Agently-Skills and Agently-Devtools companion alignment metadata.
4. [DevTools] Updated static 4.1.2 compatibility metadata to recommend agently-devtools>=0.1.4,<0.2.0.

Docs And Examples

1. [Docs] Added Execution Environment documentation in English and Chinese.
2. [Docs] Added extension-boundary guidance for core contracts, providers, built-in capabilities, and application helpers.
3. [Docs] Updated Action Runtime, observability, settings, and TriggerFlow resource guidance.
4. [Examples] Added built-in action examples for Search and Browse.
5. [Examples] Added execution-environment examples for Python, Node.js, SQLite, Browser, and health-check reuse.
6. [Examples] Added cookbook examples for model-driven action loops, routing, concurrency, reflection, and shell-policy workflows.
7. [Examples] Archived obsolete built-in tool examples.

Developer Experience

1. [Types] Added Pyright configuration for the main repository.
2. [Tests] Added compatibility registry coverage.
3. [Tests] Expanded coverage for Action Runtime, Execution Environment, EventCenter, runtime observation, and built-in action flows.

Bug Fixes

1. [Runtime] Fixed runtime console log routing behavior.
2. [Agent] Preserved default helper descriptions when custom descriptions are supplied.
3. [Compatibility] Kept published framework-code compatibility metadata stable while allowing static release metadata updates.

Full Changelog: v4.1.1...v4.1.2

v4.1.1

Highlights

• Major TriggerFlow execution lifecycle refactor with explicit close snapshots.
• New model requester protocols: OpenAI Responses API and native Anthropic Claude.
• New output validation flow with .validate(), validate_handler=, and ensure_all_keys=True.
• Updated Agently-Skills bundles for app development and migration workflows.

TriggerFlow Lifecycle Refactor

1. [TriggerFlow] Refactored execution lifecycle semantics around explicit execution objects and close snapshots.
2. [TriggerFlow] Added clearer lifecycle states for long-running executions: open, sealed, and closed.
3. [TriggerFlow] Improved auto_close and manual-close behavior so short scripts, service handlers, background workers, and streaming workflows can use different lifecycle strategies.
4. [TriggerFlow] Updated execution.close() / execution.async_close() to return the full execution close snapshot.
5. [TriggerFlow] Improved runtime stream shutdown behavior so stream consumers can drain consistently when an execution closes.
6. [TriggerFlow] Updated FastAPI Helper integration to work directly with TriggerFlow and TriggerFlowExecution under the new lifecycle model.
7. [TriggerFlow] Kept .end() and legacy result-sink behavior as compatibility surfaces, while recommending close snapshots for new code.

Features

Model Requesters

1. [ModelRequester] Added OpenAIResponsesCompatible, a built-in requester for OpenAI Responses API-shaped endpoints.
2. [ModelRequester] Added AnthropicCompatible, a native Anthropic Claude protocol requester.
3. [ModelRequester] Refactored official built-in requesters so each implementation directly follows the ModelRequester protocol without requiring third-party developers to depend on a shared prototype layer.

Output Validation

1. [Output] Added .validate() / validate_handler= support for value-level business validation on model results.
2. [Output] Added ensure_all_keys=True for strict whole-structure output enforcement.
3. [Output] Improved structured-output selection and clarified the relationship between required schema leaves, ensure_keys, ensure_all_keys, and custom validation handlers.

Updates

Request And Prompt Behavior

1. [OpenAICompatible] Added first-token timeout support for streaming requests.
2. [Prompt] Fixed and refined prompt mapping behavior.
3. [Docs] Updated prompt, output-control, model requester, and TriggerFlow examples for the 4.1.1 compatibility line.

Docs And Skills

1. [Docs] Moved official website documentation into the main repository so implementation and docs can evolve together.
2. [Skills] Updated the official Agently-Skills companion catalog for Agently 4.1.1.
3. [Skills] Simplified install bundles into app and migration:
   • app: build new Agently applications with core request, TriggerFlow, service wrapping, session, and knowledge-base guidance.
   • migration: migrate existing LangChain, LangGraph, LlamaIndex, CrewAI, or similar systems into Agently.
4. [Skills] Updated installation guidance to prefer target-agent installs over --all, avoiding unnecessary hidden agent directories in project workspaces.

Developer Experience

1. [Types] Resolved Pyright issues in core runtime paths.
2. [Examples] Made optional-dependency examples safer for static analysis.
3. [Tests] Skipped Ollama-dependent tests automatically when an Ollama server is unavailable.

Bug Fixes

1. [Runtime] Switched event logs to use runtime context settings.
2. [DevTools] Updated the evaluation example executor to match current runtime behavior.

Full Changelog: v4.1.0...v4.1.1

v4.1.0

Features

Action Runtime

1. [Action] Replaced the old single-layer tool path with a three-layer Action Runtime: ActionRuntime, ActionFlow, and ActionExecutor.
2. [Action] Added native support for local functions, MCP servers, Python/Bash sandboxes, and custom execution backends.

TriggerFlow

1. [TriggerFlow] Renamed runtime events to the triggerflow.* namespace, while keeping compatibility aliases for legacy workflow.* and trigger_flow.* subscriptions.
2. [TriggerFlow] Published Mermaid definitions on workflow definition runtime events so execution graphs can show the full static flow.

Runtime Logging

1. [Runtime] Added debug log profiles (off, simple, detail) and switched the default runtime output to quiet mode.
2. [Runtime] Unified console and storage sinks around the same profile model so summary and detail rendering stay consistent.

Updates

Agent And Core

1. [Agent] Exported Agent as a default top-level import from agently.
2. [Core] Normalized RuntimeContext internals and consolidated the runtime log helpers.

Docs And Examples

1. [Docs] Refreshed the README for 4.1.0 and updated the agently-devtools compatibility line to agently >=4.1.0,<4.2.0.
2. [Examples] Added Action Runtime samples, refreshed DevTools examples to use the Agently shortcut, and archived obsolete tool/MCP demos.

Bug Fixes

1. [Runtime] Fixed duplicate streaming done emission.
2. [Response] Fixed the JSON repair fallback for structured streaming.

v4.0.9

v4.0.9

Features

Runtime Observation And DevTools Companion

1. [Runtime] Added the runtime event bus and run-lineage foundation for request, model, agent-turn, action, and workflow observation.
2. [Runtime] Added model request observation lifecycle events, including prompt build, request, streaming, retry, completion, and meta stages.
3. [DevTools] Introduced agently-devtools as an optional companion package for local observation, evaluation, logs, and playground workflows.
4. [DevTools] Added public integration entrypoints around ObservationBridge and create_local_observation_app.

TriggerFlow

1. [TriggerFlow] TriggerFlow executions now emit workflow definitions so local execution graphs can display the full static flow, including branches that have not run yet.
2. [TriggerFlow] Added chunk-level runtime scope, including signal metadata, runtime input and output payloads, and origin-chunk metadata on workflow stream and result events.
3. [TriggerFlow] Added flow definition export and import through JSON and YAML, plus Mermaid generation for reviewable workflow assets.
4. [TriggerFlow] Added execution state save and load support for restart-safe pause and resume workflows.
5. [TriggerFlow] Added sub-flow support, runtime resources, and stronger contract typing, including FastAPI Helper alignment with TriggerFlow contracts.

Tools And Developer Experience

1. [Tools] Added Playwright and PyAutoGUI-powered built-in browsing support, with fallback integration in Browse.
2. [Skills] Published the official installable Agently skills catalog.

Updates

Request, Response, And Settings

1. [Request] Split ModelRequest response and result handling into clearer response-side modules.
2. [Response] Refined response reuse paths around ModelResponse and ModelResponseResult.
3. [Settings] Added auto_load_env=True support to settings.load_settings() and to entities that expose .load_settings().
4. [Prompt] Added save_to and encoding support to .get_json_prompt() and .get_yaml_prompt().
5. [Output] Added Enum support in output format declarations.
6. [Utils] Renamed RuntimeData to StateData while keeping compatibility aliases.

Session And Tooling

1. [Session] Streamlined session resize pipeline and handler APIs, with follow-up typing and behavior fixes.
2. [Tools] Refactored tool handlers and multi-round action flow to make tool execution paths easier to observe and maintain.

Bug Fixes

1. [Runtime] Fixed parsed model completion payload fields in runtime observation.
2. [TriggerFlow] Fixed cases where flow definition export or Mermaid generation could miss chunks.
3. [Prompt] Fixed long-string handling in .load_yaml_prompt() and .load_json_prompt().
4. [Settings] Fixed auth-header handling and preserved compatibility between options and request_options.
5. [Data] Fixed list-at-root handling in DataLocator.
6. [Session] Fixed chat-history mutation bugs caused by pointer behavior in session helpers.

v4.0.8

Agently v4.0.8

Features

1. New integration: Agently FastAPIHelper

FastAPIHelper is a new FastAPI integration that turns Agently providers into HTTP APIs with minimal setup.
It supports BaseAgent, ModelRequest, TriggerFlow, TriggerFlowExecution, and custom generator functions, with unified request/response wrapping for POST, GET, SSE, and WebSocket.

Related examples:

• fastapi_helper_agent_ollama.py
• fastapi_helper_triggerflow_ollama.py
• fastapi_helper_agent_request.py

from agently import Agently
from agently.integrations.fastapi import FastAPIHelper
import uvicorn

agent = Agently.create_agent()
agent.role("You are a concise and helpful assistant.", always=True)

app = FastAPIHelper(response_provider=agent)
app.use_post("/agent/chat").use_get("/agent/chat/get").use_sse("/agent/chat/sse").use_websocket("/agent/chat/ws")

if __name__ == "__main__":
    uvicorn.run(app, host="127.0.0.1", port=8000)

Quick test with cURL:

# POST (non-streaming)
curl -sS -X POST "http://127.0.0.1:8000/agent/chat" \
  -H "Content-Type: application/json" \
  -d '{
    "data": { "input": "Say hello in one short sentence." },
    "options": {}
  }'

{
  "status": 200,
  "data": "Hello! Nice to meet you.",
  "msg": null
}

# SSE (streaming)
curl -N -G "http://127.0.0.1:8000/agent/chat/sse" \
  --data-urlencode 'payload={"data":{"input":"Count 1 to 3"},"options":{}}'

data: {"status": 200, "data": "1", "msg": null}

data: {"status": 200, "data": ", 2", "msg": null}

data: {"status": 200, "data": ", 3", "msg": null}

2. Session system rewrite (Session + SessionExtension)

A redesigned session system is now built into the default Agent extension stack.
It introduces Session as a first-class core object with full_context, context_window, and memo, plus structured import/export (JSON / YAML) and customizable analysis/execution handlers for memory control.

Related example:

• session.py

from agently import Agently

agent = Agently.create_agent()

agent.activate_session(session_id="demo_session")
agent.input("Remember this: my favorite city is Chengdu.").streaming_print()
agent.input("What is my favorite city?").streaming_print()

agent.deactivate_session()
agent.input("What is my favorite city?").streaming_print()

Updates

1. TriggerFlow runtime improvements

1. Added .set_concurrency() to TriggerFlowExecution for dynamic runtime concurrency control.
2. Added FunctionShifter.asyncify_sync_generator() to bridge sync generators into async streaming pipelines.
3. FastAPIHelper can now forward concurrency options to TriggerFlowExecution.

Related examples:

• 11-triggerflow-03_concurrency.py
• 11-triggerflow-10_runtime_stream.py
• fastapi_helper_triggerflow_ollama.py

2. Tooling and MCP compatibility

1. Added built-in Cmd tool (agently.builtins.tools.Cmd) with allowlist and workdir guardrails.
2. Added BuiltInTool protocol and tool_info_list-based built-in tool integration path.
3. Updated MCP integration requirement to fastmcp>=3.

Related examples:

• cmd.py
• 10-mcp.py

3. Prompt and API behavior refinements

1. Moved .get_json_prompt() and .get_yaml_prompt() to ConfigurePromptExtension.
2. Added prompt.add_current_time setting with shared TimeInfo utility support.
3. Improved compatibility handling for deprecated response content arguments.
4. set_debug_console("ON") is now deprecated and has no runtime effect.
5. ChatSessionExtension is now deprecated in favor of SessionExtension.

Related examples:

• add_current_time_to_prompt.py
• 04-configure_prompt.py

4. Documentation and examples refresh

1. Reorganized and expanded examples (basic, step_by_step, and FastAPI helper scenarios).
2. Added coding-agent docs and cheatsheets.
3. Updated README/README_CN and project legal docs (LICENSE/CLA/TRADEMARK related updates).

Related links:

• step_by_step examples
• docs_for_coding_agent/README.md
• cheatsheet_for_coding_agent_en.txt

5. Stability and bug fixes

1. Fixed incorrect prompt slot assignment in .role().
2. Fixed potential deadlock when fetching result in finally event flows.
3. Fixed agent settings propagation issues.
4. Fixed DataFormatter handling for JSON Schema additionalProperties=false.
5. Improved typed output handling for nested Pydantic target types.
6. Added wildcard data path support (for example: resources[*].title).

---

Full Changelog: v4.0.7...v4.0.8

v4.0.7

Features

TriggerFlow Concurrency Control

1. [TriggerFlow]: Global concurrency control for each execution (pass concurrency when creating execution or starting flow).
2. [TriggerFlow]: .batch() supports concurrency control.
3. [TriggerFlow]: .for_each() supports concurrency control.
4. [Example]: New concurrency control example.

Python Sandbox Utility

1. [Utils]: New Python Sandbox utility (safer isolated execution environment).

Updates

TriggerFlow

1. [TriggerFlow]: .to() / .batch() support tuple form (name, handler) to create chunks quickly.
2. [TriggerFlow]: Use TriggerFlow.chunk() in BaseProcess so chunks are registered properly.
3. [TriggerFlow]: Auto-generated id for quick-created chunks.
4. [Examples]: New TriggerFlow RESTful API + FastAPI example.
5. [Examples]: New example for quick chunk creation.

Agent Request

1. [Request]: Request instance adds .start() / .async_start() methods.
2. [Request Settings]: specific supports None.
3. [Request Settings]: auto_load_env added to .set_settings(), and core classes now use settings.set_settings uniformly.

Prompt / Configure Prompt

1. [Prompt]: .get_yaml_prompt() / .get_json_prompt() renamed from .to_*.
2. [Prompt]: .load_yaml_prompt() / .load_json_prompt() support Path input and key-path extraction.
3. [Prompt]: Add encoding parameter to .load_yaml_prompt() / .load_json_prompt().
4. [Prompt]: Fix prompt type misjudgement.
5. [Prompt]: DataFormatter.substitute_placeholder() separated from Prompt into utils.

Debug / Developer Experience

1. [Debug]: Console printing beautified and flushed for smoother output.
2. [Examples]: Provide function calling & reasoning examples for specific type.
3. [Examples]: Add uvicorn start script.

Bug Fixes

1. [TriggerFlow]: Fix batch wait bug.
2. [Prompt]: Ignore None in output configure prompt generation.
3. [Prompt]: Ensure yaml.safe_dump() uses sort_keys to keep original order.
4. [Request]: .get_result() should be sync (fixed in range).
5. [Misc]: Fix LazyImport error causing main package import issues.
6. [MCP]: Support MCP responses without structured_content or non-TextContent.
7. [Auth]: Avoid sending auth when none is configured.
8. [Compatibility]: Ensure compatibility for uncertain types like dict / dict[Any, Any].

v4.0.6

Features

ChromaDB Integrations

You can use Agently ChromaDB Integrations to simplify the use case of ChromaDB

from agently import Agently
from agently.integrations.chromadb import ChromaData, ChromaEmbeddingFunction
from chromadb import Client as ChromaDBClient

embedding = Agently.create_agent()
embedding.set_settings(
    "OpenAICompatible",
    {
        "model": "qwen3-embedding:0.6b",
        "base_url": "http://127.0.0.1:11434/v1/",
        "auth": "nothing",
        "model_type": "embeddings",
    },
).set_settings("debug", False)

embedding_function = ChromaEmbeddingFunction(agent=embedding)

chroma_data = ChromaData(
    [
        {
            "document": "Book about Dogs",
            "metadata": {"book_name": "🐶"},
        },
        {
            "document": "Book about cars",
            "metadata": {"book_name": "🚗"},
        },
        {
            "document": "Book about vehicles",
            "metadata": {"book_name": "🚘"},
        },
        {
            "document": "Book about birds",
            "metadata": {"book_name": "🐦‍⬛"},
        },
    ],
)

chromadb = ChromaDBClient()
collection = chromadb.create_collection(
    name="test",
    get_or_create=True,
    metadata={
        "hnsw:space": "cosine",
    },
    configuration={
        "embedding_function": embedding_function,
    },
)

collection.add(**chroma_data.get_kwargs())
print("[ADD]:\n", chroma_data.get_original_data())

result = collection.query(query_texts=["Book about traffic"])
print(result)

Updates

TriggerFlow

1. .when() support 'and', 'or' and 'simple_or' mode. [Example Code]
2. Developers can use .save_blue_print() to export blue print data from trigger flow instance or from blue print instance and use .load_blue_print() to import blue print data into other trigger flow instance or blue print instance. [Example Code]

Agent Request

Better Prompt DX

1. [Prompt]: New prompt slots options to allow developers to customize single request / agent request options.
2. [Prompt]: New prompt slots examples to help developers provide one-shot / few-shots examples.
3. [Prompt]: Update agent.prompt to allow developers export prompt text or messages only. [Example Code]
4. [Prompt]: New settings prompt.prompt_title_mapping to help developers to customize title of different prompt slots. [Example Code]

Configure Prompt Update

5. [Configure Prompt]: Support the expression of Agently output format. [Example Code]

Request Settings Updates to Support Local Deployed Model Service

6. [Request Settings]: Support customized authorization headers [Example Code]
7. [Request Settings]: Developers can use full_url to provide full model request URL in case that sometimes the model URL does not follow the rule of OpenAI base URL.
8. [Request Settings]: Developers can use api_key in request settings now, it works all the same as auth.

Agent Response

1. [Instant Mode]: StreamingData add attribute full_data which contains current completed streaming data.
2. [Result]: Former .get_result() method is renamed as .get_data() which will return parsed data. New .get_result() method will return AgentlyResponseResult instance which contains more attributes to help developers to collect information of result.
3. [Response Generator Type]: New response generator type typed_delta (and now .get_generator() and .get_async_generator() will use argument type instead of argument content).
4. [Response Event]: Add new response event tool_calls which can be consumed in generator type typed_delta and instant / streaming_parse. [Example Code]

Plugins

1. [Agent Extension Core]: Update extension handler slots to request_prefixes, broadcast_prefixes, broadcast_suffixes and finally
2. [Tools]: Built-in tool Search new support argument options to customize more options configures. [Example Code]

Utils

1. [FunctionShifter]: New decorator @auto_options_func to help developers to create a function that will ignore undefined key arguments that passed by caller (useful when model try to pass undefined arguments to a tool function).

v4.0.5

Key Feature Updates

TriggerFlow

1. Rewrite for each process (.for_each()) to support nested for each loops perfectly. [Example Code]
2. Add .____(<comments>, log_info=<True | False>, print_info=<True | False>, show_value=<True | False>) to help developers to write flow chain beautifully.
3. Add .when() to support developers to wait chunk done event, runtime data change event, flow data change event or customize event and trigger the next actions. [Example Code]
4. Add .collect() to support developers to wait and collect parallel branches. [Example Code]
5. Rewrite and update match case process, now developers can use .match(mode=<"hit_all" | "hit_first">) to set different judgement hit strategy. [Example Code]

You can also explore more example codes in TriggerFlow examples dir.

Prompt Configures

In Agently v3, developers loved YAML-Prompt very much. Now we update this feature to Prompt Configures!

Mappings replacing in any prompt settings

Now developers can use mappings parameter in any prompt setting methods. Use case examples: agent.input("${user_input}", mappings={ "user_input": beautify(user_input) }) or agent.set_agent_prompt("instruct", "You're a ${ role }", mappings={ "role": roles[current_role] }).

Developers can use mapping replacing feature to replace placeholder ${ <variable name> } in string content. Dvelopers can also use it to replace key name or value in dictionary like { "${ key_to_be_replaced }": "${ value_to_be_replaced_directly }" }.

Check here to see Example Code

YAML and JSON format supported!

Now developers can use both YAML and JSON format data to configure agent behaviors!

• YAML-Prompt Example Code:

  • Configure File: https://github.com/AgentEra/Agently/blob/main/examples/configure_prompt/yaml_prompt.yaml
  • Execution Code: https://github.com/AgentEra/Agently/blob/main/examples/configure_prompt/load_yaml_prompt.py

• JSON-Prompt Example Code:

  • Configure File: https://github.com/AgentEra/Agently/blob/main/examples/configure_prompt/json_prompt.json
  • Execution Code: https://github.com/AgentEra/Agently/blob/main/examples/configure_prompt/load_json_prompt.py

Built-In Tools

We added two built-in tools Search and Browse which can be registered to agent or be used independently. You can use from agently.builtins.tools import Search, Browse to import and use them.

Search tool can search information from DuckDuckGo, Bing, Google, Yahoo, Wikipedia via package ddgs and search document from arXiv.

Browse tool use BeautifulSoup4 to fetch most common website page content for agent.

Check here to see Example Code

Instant Mode

We add a new attribute .wildcard_path to instant mode event data for developers to watch items in list easier. Now developers can use code like if data.wildcard_path == "root_key.list[*]:" to watch and handle every item in root_key.list from Agently agent response in instant mode.

Check here to see Example Code

Other Updates

• Optimized LazyImport to support the situation when the package's import name is different from the install name.
• Optimized tool using logic to catch exceptions when calling the tools instead of preventing the agent request process.
• Many other updates and bug fixes...

=========

We'll keep updating and welcome all users to express your ideas or discuss with us in https://github.com/AgentEra/Agently/discussions

Have fun and happy coding!

v4.0.3

Some major bugs fixed and add more examples:

Trigger Flow Feature Examples: https://github.com/AgentEra/Agently/tree/main/examples/trigger_flow

Trigger Flow WebSocket Server Example: https://github.com/AgentEra/Agently/tree/main/examples/trigger_flow/ws_server