#149149th of 153 in Agent frameworks and SDKs

deepresearchagent

Python runtime for agents that version resources and self-improve

Stars
3.6k
License
MIT
Last commit
May 2026
Last release
Feb 2026
Language
Python
Stars, last 29 weeks+261
25 Apr 2026: 3,311 stars2 May 2026: 3,321 stars9 May 2026: 3,335 stars16 May 2026: 3,345 stars23 May 2026: 3,356 stars30 May 2026: 3,369 stars6 Jun 2026: 3,400 stars13 Jun 2026: 3,416 stars20 Jun 2026: 3,431 stars27 Jun 2026: 3,437 stars4 Jul 2026: 3,444 stars11 Jul 2026: 3,454 stars18 Jul 2026: 3,460 stars25 Jul 2026: 3,469 stars1 Aug 2026: 3,477 stars8 Aug 2026: 3,488 stars15 Aug 2026: 3,495 stars22 Aug 2026: 3,508 stars29 Aug 2026: 3,519 stars5 Sept 2026: 3,523 stars12 Sept 2026: 3,527 stars19 Sept 2026: 3,535 stars26 Sept 2026: 3,541 stars3 Oct 2026: 3,545 stars10 Oct 2026: 3,549 stars17 Oct 2026: 3,559 stars24 Oct 2026: 3,561 stars31 Oct 2026: 3,566 stars7 Nov 2026: 3,568 stars14 Nov 2026: 3,572 stars

3,311 on 25 Apr 20263,572 on 14 Nov 2026

From GitHub's daily star counts.

Checked on GitHub.

Overview

Deep Research Agent defines two protocol layers: RSPL registers prompts, agents, tools, environments and memory as versioned resources, and SEPL proposes, assesses and commits changes with lineage and rollback. It ships a tool-calling agent plus optimizers (reflection, GRPO, Reinforce++), tracing and MMEngine-style configs. The README documents only one example script, run with an OpenRouter-style model name.

Who it is for: Researchers and engineers building self-improving agent systems in Python

Strengths

  • Versioned resources with rollback and auditable lineage for prompts, tools and memory
  • Pluggable optimizers including reflection, GRPO and Reinforce++
  • Structured traces and memory events help analyze failed runs
  • MMEngine-style configs compose agents, tools, environments and models

Weaknesses

  • No Docker or compose files provided
  • README gives no benchmarks or results for the self-evolution loop
  • Protocol terminology raises the learning curve for simple agent use

What it needs

  • Needs LLM provider API key (e.g. OpenRouter)
  • Models: openrouter/gpt-4o

What changed

From the release notes. No flag means the note does not say so, not that the upgrade is safe.

Also in Agent frameworks and SDKs

See all 153
Also in Agent frameworks and SDKs
RankProjectScore
1ppt-masterAgent skill that turns documents into natively editable PowerPoint decks Live demo ↗ (opens in a new tab)78k starsMIT96 out of 100
2copilotkitReact and Angular SDK for adding agent chat and generative UI to apps38.8k starsMIT92 out of 100
3openai-agents-pythonPython SDK for multi-agent workflows with handoffs, guardrails and tracing30.7k starsMIT92 out of 100
#4mastraTypeScript framework for building AI agents, workflows and MCP servers29.6k starscustom license92 out of 100
#5browser-usePython library that lets an LLM agent control a web browser Live demo ↗ (opens in a new tab)121.4k starsMIT90 out of 100