Superagentic AI

113 posts

Superagentic AI banner
Superagentic AI

Superagentic AI

@SuperagenticAI

Full Stack Agentic AI Company based in 🇬🇧 and 🇺🇸 , building agent developer tools for Agent Engineering/Experience/Orchestration. Research on Quantum AI

London 🇬🇧 | SF 🌉 Se unió Nisan 2025
1 Siguiendo103 Seguidores
Tweet fijado
Superagentic AI
Superagentic AI@SuperagenticAI·
🇺🇸 We are live in the USA .. Superagentic AI Corporation.. From London 🇬🇧 to the United States 🇺🇸 Superagentic AI is now live in the US. Excited to collaborate with the Bay Area agentic AI ecosystem. 👉 super-agentic.ai #AgenticAI #SanFrancisco #London
English
0
0
0
294
Superagentic AI
Superagentic AI@SuperagenticAI·
Our Gemma 4 MLX version now available on Hugging Face for our experimentation. 💻 Gemma 4 31B IT to an MLX 4-bit format so it runs efficiently on Apple Silicon 128GB MacBook. 🖥️ huggingface.co/SuperagenticAI… 🙏Once official Gemma 4 support lands cleanly upstream in MLX
English
0
0
1
692
Superagentic AI
Superagentic AI@SuperagenticAI·
🗣️While most people were still discussing the Meta Harness paper, We shipped a working open source implementation. 💻metaharness is a Codex-first Python 🐍 library for self-optimizing the harness around coding agents. benchmark #AgentEngineering #MetaHarness
English
1
0
0
50
Superagentic AI
Superagentic AI@SuperagenticAI·
💡Harness Engineering: Why It's Suddenly the Hottest Topic in AI Agent Engineering 🌉We are hosting in person event in San Francisco to talk about it. Read our detailed blog and RSVP to the event in the links below 👇
English
1
0
0
29
Superagentic AI
Superagentic AI@SuperagenticAI·
New tutorial: Turbocharge Pydantic AI + SurrealDB RAG with TurboAgents and TurboQuant. Same app, same stack, retriever-only change. @pydanti_ai @SurrealDB 📚 All the useful links 🔗 below  👇
English
1
0
2
83
Superagentic AI
Superagentic AI@SuperagenticAI·
As models evolve, repo instruction files like AGENTS.md and SKILL.md can drift and require re-optimization. That’s why we built CodexOpt: a repo-native way to benchmark and optimize coding-agent instructions using GEPA-inspired feedback and prompt-learning ideas. Read 👇 #Codex
English
1
0
1
68
Superagentic AI
Superagentic AI@SuperagenticAI·
🧬 SuperOptiX now supports Agent 2 Agent (A2A) v1. Finally, v1 is the first stable, production-ready release of the Agent-to-Agent protocol. 📙Detailed blog post: 📷 A2A v1 in SuperOptiX: Expose, Connect, and Orchestrate AI Agents super-agentic.ai/resources/supe…
English
1
0
1
42
Superagentic AI
Superagentic AI@SuperagenticAI·
We launched "Code Mode" in RLM Code RLM Code now supports a practical CodeMode workflow with MCP backends - strategy=codemode for UTCP-style CodeMode MCP - Cloudflare remote MCP support via mcp-remote super-agentic.ai/resources/supe…
English
0
0
1
148
Superagentic AI
Superagentic AI@SuperagenticAI·
🚀 RLM Code: A Research Playground for Recursive Language Models Run the experiment yourself: - recursive REPL workflows - trajectory replay - secure sandboxes (Docker, Monty, Apple Container, Modal/E2B) - observability (MLflow, Logfire, LangSmith, LangFuse,)
English
0
0
1
102
Superagentic AI
Superagentic AI@SuperagenticAI·
SuperOptiX is now open source. From DSPy-first origins (July 2025) to a cross-framework agent optimization engine: - minimal native pipelines - GEPA via --optimize - Experimental RLM Support GitHub: github.com/SuperagenticAI…
English
0
0
1
122
Superagentic AI
Superagentic AI@SuperagenticAI·
We released the @AmpCode ACP bridge to support AMP in all ACP ecosystem of editors and clients.
Shashi 🇬🇧🇺🇸@Shashikant86

🎇Glad to announce that @SuperagenticAI is Introducing ACP Bridge to Amp Code @AmpCode Now you can use incredible power of Amp Code with all the available Agent Client Protocols(ACP) supported clients by @zeddotdev I used all available coding agents in the market Claude Code, Codex, Gemini CLI, droid, opencode, Kiro, Cursor Agent CLI, Letta-Code etc (You name it) and built our own SuperQode but Amp Code is something special harness technically and architecturally unique that uses combination of small and large language models based on the task. Hat's off @beyang @sqs and Team As SuperQode is ACP client in Python 🐍, we don't want miss the power of AMP and it was missing from the existing client. So we added it. There is amazing project from @zhangjintao9020 to support TS based workflow but we needed Python support too! Now you can use Amp Code across other ACP clients, both Python and TypeScript based. 🎯 Try it today, It's fully Open Source! 🕸️ super-agentic.ai/acp-amp 💻 GitHub: github.com/SuperagenticAI… 📚 Docs: superagenticai.github.io/acp-amp/

English
0
0
0
86
Superagentic AI
Superagentic AI@SuperagenticAI·
🎆 Happy New Year 2026🎇
English
0
0
0
80
Superagentic AI
Superagentic AI@SuperagenticAI·
🎆Year In Review 2025! 🎆
Shashi 🇬🇧🇺🇸@Shashikant86

✨ Year in Review 2025: From Apple  to Superagentic AI: Building an Agentic Company of One ✨ ⚡️One Year, Two Lives, 4 Months of  and 8 Months of Superagentic AI. The last eight months have been about building with focus, speed, and conviction. This year was about: 🧠 shifting from User Experience, Developer Experience to Agent Experience ⚙️ building systems, tools, and foundations for agentic intelligence 🚀 shipping at high velocity with focus and leverage 🌍 growing community alongside research and open work 🧩 learning how much one person can build with multiple agents Here is what Company of One Built in 8 month at Superagentic 🧠 4 Products (SuperOptiX, CodeOptiX, SuperRadar, SpecMem) 🧪4 Agentic AI Business Solutions (Agentic AQ, Agentic DevOps, Agentic Builder, Agent Optimization) 🔓 14 Open source projects & 1 Research Paper on Agent Optimization 📚 47 Blog post Content 🌍 Community & ecosystem Founded the London Agentic AI community (0 → 1,400+ members), Hosted 3 meetups, attended 50+ 🎤Spoke at conferences and meetups in London 🌉Partnered with ODSC AI and engaged with global communities 🇬🇧Participated in policy and ecosystem discussions in the UK ✍️I wrote this as an honest year-in-review. This post is a reflection on that journey the shift from developer experience to agent experience, from stability to uncertainty, from working inside a large organization to building foundations for agentic systems from scratch 👇 #YearInReview2025 #AgenticAI

English
0
0
0
80