LlamaIndex
banner
llamaindex.bsky.social
LlamaIndex
@llamaindex.bsky.social
Build AI agents over your documents
🦔 Thanks to PostHog’s observability integration, the demo automatically tracks OpenAI usage, including:
• Token consumption
• Cost breakdown
• Latency metrics

🎥 Check out the video below to see it in action 👆
February 13, 2026 at 5:02 PM
Read @jerryjliu0's full blog on long horizon document agents: www.llamaindex.ai/blog/long-h...
Long Horizon Document Agents
LlamaIndex is a simple, flexible framework for building knowledge assistants using LLMs connected to your enterprise data.
www.llamaindex.ai
February 12, 2026 at 4:58 PM
2026 is shaping up to be the year agents evolve from "workflows" to "employees" - and we're building the document processing infrastructure to make this possible.
February 12, 2026 at 4:58 PM
🎯 The interface shifts from chat boxes to "agent inboxes" that manage ongoing document tasks with clear status and context
⚡ This enables true automation of multi-step knowledge work - from due diligence memo updates to contract redline collaboration loops
February 12, 2026 at 4:58 PM
🔄 These agents can continuously monitor events like document changes, comments, and deadlines - not just respond to chat prompts
📝 They maintain persistent task backlogs and can collaborate iteratively on living documents like FAQs, PRDs, and legal contracts
February 12, 2026 at 4:58 PM
We're excited about how this translates to knowledge work automation, particularly over documents. Let's take a look at "Long Horizon Document Agents"

🕰️ Agents are evolving to work autonomously over weeks, not just minutes, handling complex document tasks end-to-end.
February 12, 2026 at 4:58 PM
Read the full blog by Logan on how he views this evolution of open source projects: www.llamaindex.ai/blog/on-the...
On the Incoming Slopocalypse and the Death(?) of Open Source
LlamaIndex is a simple, flexible framework for building knowledge assistants using LLMs connected to your enterprise data.
www.llamaindex.ai
February 11, 2026 at 5:04 PM
But open source isn't dead - it's evolving. We're shifting toward hackable reference implementations, community-driven knowledge sharing, and agent-friendly codebases that work with AI tools rather than against them.
February 11, 2026 at 5:04 PM
💪 Personal skill development suffers when developers rely too heavily on AI assistance
🧠 Knowledge sharing is shifting as LLMs become the frontend for learning
February 11, 2026 at 5:04 PM
📦 Install: 𝘶𝘷 𝘵𝘰𝘰𝘭 𝘪𝘯𝘴𝘵𝘢𝘭𝘭 𝘭𝘰𝘣𝘴𝘵𝘦𝘳𝘹 --𝘱𝘳𝘦𝘳𝘦𝘭𝘦𝘢𝘴𝘦=𝘢𝘭𝘭𝘰𝘸
📚 Read more: github.com/AstraBert/w...
🦙 Sign up to LlamaCloud: cloud.llamaindex.ai/signup
workflows-acp/packages/lobsterx/README.md at main · AstraBert/workflows-acp
ACP wrapper for LlamaIndex Agent Workflows. Contribute to AstraBert/workflows-acp development by creating an account on GitHub.
github.com
February 9, 2026 at 5:04 PM
It’s fully self-hostable, can be run as a uv tool or Docker container, and works out of the box as a Telegram bot 💬
February 9, 2026 at 5:04 PM
Designed with a safety-first mindset, the agent runs on AgentFS (by @tur.so) to protect your real filesystem and intentionally avoids full shell access to prevent security-critical or destructive operations 🔒
February 9, 2026 at 5:04 PM
LobsterX is built on top of our Agent Workflows and leverages LlamaCloud for document parsing, structured data extraction, and classification via powerful, modular tools🛠️
February 9, 2026 at 5:04 PM
Try it out through the cloud UI or the API and see the difference visual citations make for your document extraction pipeline. Sign up to LlamaCloud to get started: https://cloud.llamaindex.ai?utm_source=socials&utm_medium=li_social
February 6, 2026 at 5:18 PM
📄 Perfect for compliance, auditing, and quality assurance workflows where traceability matters

This makes LlamaExtract even more reliable for production document processing where you need to show your work and validate results.
February 6, 2026 at 5:18 PM
📍 Precise bounding boxes highlight the exact location of extracted data in your source documents
🔍 Full citation transparency so you can verify and trust your extraction results
🚀 Also available through our API for seamless integration into your applications
February 6, 2026 at 5:18 PM