Connect agents to private data, retrieval systems, and tools with a broad framework for context-aware applications.
Knowledge & RAG
Back to discovery
Atom feed
LlamaIndex
Haystack
Deer Flow
Knowledge & RAG
Agentos
TypeScript AI agent framework: cognitive memory, runtime tool forging, multi-agent orchestration, 11 LLM providers.
Worth exploring for
Data-connected agents and retrieval workflows
In our collection
4 releases
Source
Official GitHub release feed
Follow the changes
The release trail
Original notes, ready to explore. Open a release to see what changed.
Agentosv0.10.18
From the release notes
0.10.18 (2026-09-12) fix(providers): don't throw on reasoning-only /v1/responses output (e116f4ed5cbcecb35f0ddbb350ff2fa0ea42eec3)
Agentosv0.10.17
From the release notes
0.10.17 (2026-09-11) fix(providers): route /v1/responses when system content is cache-marked blocks (82f028e55e23c6b5f03413be2bdff819fef76ca6)
Agentosv0.10.16
From the release notes
0.10.16 (2026-09-10) fix(providers): correct GPT-5.6 cache retention and add the shipped 5.6 siblings (7f55072d02ee1d73383539312ebba2f5c13fbeb6)
Agentosv0.10.15
From the release notes
0.10.15 (2026-09-10) feat(providers): support GPT-6 (gpt-6-astra) across the OpenAI param guards (f33595810842c5a0e8a411d104b655c07ae938ed)
A collected snapshot, not the complete archive.
Keep connecting the dots
There’s more where that came from.
Design production-ready pipelines and agents for search, retrieval-augmented generation, and question answering.
Knowledge & RAGAn open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of tasks that could take minutes to hours.
Knowledge & RAG