# trpc-agent-python

> tRPC-Agent-Python provides an end-to-end foundation for agent building, orchestration, tool integration, session and long-term memory, service deployment, and observability, so you can ship reliable a

- **URL**: https://www.freshcrate.ai/projects/trpc-agent-python
- **Author**: trpc-group
- **Category**: AI Agents
- **Latest version**: `v1.1.6` (2026-06-03)
- **License**: NOASSERTION
- **Source**: https://github.com/trpc-group/trpc-agent-python
- **Language**: Python
- **GitHub**: 65 stars, 3 forks
- **Registry**: github
- **Tags**: `python`

## Description

tRPC-Agent-Python provides an end-to-end foundation for agent building, orchestration, tool integration, session and long-term memory, service deployment, and observability, so you can ship reliable and extensible AI applications faster.

## Recent releases

| Version | Date | Urgency | Changes |
| --- | --- | --- | --- |
| `v1.1.6` | 2026-06-03 | High | ### Features  * Skill: Added a recoverable Cube sandbox runtime for skills, including `CubeClientConfig`, a unified `create_cube_sandbox_client` entry point, optional `auto_recover` support in `CubeSandboxClient`, sandbox lifecycle helpers, and direct `CubeWorkspaceRuntime` creation from the client. * Skill: Unified skill load/run/exec/stager paths around repository-level workspace runtime resolution via `repository.get_workspace_runtime(ctx)`, so tools under the same skill repository share o |
| `v1.1.5` | 2026-05-19 | High | ## [1.1.5](https://github.com/trpc-group/trpc-agent-python/releases/tag/v1.1.5) (2026-05-19)  ### Features  * Tools: Added `StreamingProgressTool` with matching `ToolsProcessor` plumbing so tools can surface intermediate progress as `partial=True` events while still emitting a single final `function_response`; included `BaseTool` streaming hooks, the `llmagent_with_streaming_progress_tool` example and verification script. * Eval: Added `RemoteEvalService` to drive evaluations against agents |
| `v1.1.4` | 2026-05-13 | High | ### Bug Fixes  * Tools: Removed default `mempalace_tool` exports from `trpc_agent_sdk.tools` to avoid forcing MemPalace optional dependencies during base package import. |
| `1.1.2.post1` | 2026-04-29 | High | ### Features  * Session: Updated session summarization to retain full conversation history while marking summarized events as model-invisible. * Session: Added backend-threaded summarization execution to avoid blocking front-end conversation turns. * Skill: Added multi-user support for skill operations.  ### Bug Fixes  * Code Execution: Fixed the conflict between code execution and tool invocation where tool data could be lost after code execution. * MCP: Added support for parsing and r |
| `v1.1.2` | 2026-04-24 | High | ### Features  * Telemetry: Added OpenTelemetry metrics reporting and introduced `custom_metrics` to support framework metric reporting when parsing remote agent responses. * Tools: Added `web_search` with DuckDuckGo and Google providers, and added `web_fetch` for webpage content retrieval. * Docs/Examples: Added usage documentation and examples for `web_search` and `web_fetch`. |
| `v1.1.1` | 2026-04-20 | High | ### Features  * Storage: Added the `usage_metadata` field to SQL storage and introduced automatic migration for missing columns. * Skill: Added cross-session skill state persistence so loaded skills can be reused across sessions, reducing repeated skill loading and unnecessary retry turns. * Skill: Added skill install/uninstall awareness so the model can detect skill lifecycle changes and avoid missing-skill lookups or calls to uninstalled skills. * Session: Added `usage_metadata` support i |
| `v1.1.0` | 2026-04-07 | High | ### Features  * Unified Agent framework with `LlmAgent`, `LangGraphAgent` and `TransferAgent` * Multi-agent orchestration with built-in `Chain`, `Parallel`, and `Cycle` patterns, plus Team and nested Team collaboration * Human-in-the-loop workflows with pause, review, and resume support for long-running tasks * Rich tool ecosystem including built-in file/shell tools, MCP tools, LangChain tools, and extensible third-party integrations * Extensible Skill system with local and HTTP distributi |

## Citation

- HTML: https://www.freshcrate.ai/projects/trpc-agent-python
- Markdown: https://www.freshcrate.ai/projects/trpc-agent-python.md
- Dependencies JSON: https://www.freshcrate.ai/api/projects/trpc-agent-python/deps

_Generated by freshcrate.ai. Indexes github releases for AI-agent ecosystem packages._