Graph Agents
Alex Clarke edited this page 2026-08-31 16:41:34 -06:00
Clone

Wiki Page Revisions

23 Commits

Author SHA1 Message Date
Dark-Alex-17 2ff6981866 docs: corrected the graph-agent parallel reducer gotcha 2026-08-31 16:41:34 -06:00
Dark-Alex-17 5c50d3131e docs: Added the linux GNU vs MUSL differentiation for DuckDB RAG drivers 2026-08-28 22:33:30 -06:00
Dark-Alex-17 bbbdc74fb6 docs: Added documentation for the new mcp allowlist feature 2026-08-27 16:05:43 -06:00
Dark-Alex-17 fcab6ac583 docs: Created documentation on the new background job subsystem 2026-08-26 14:54:55 -06:00
Dark-Alex-17 c666b53565 docs: Added documentation of the new timeout settings 2026-08-14 15:37:08 -06:00
Dark-Alex-17 f03d49ea65 docs: Improved and updated wiki docs on RAGs 2026-08-12 13:05:40 -06:00
Dark-Alex-17 ee8b5781be docs: Document the driver prompt at agent RAG init and the duckdb two-file pairing
Agent startup and graph rag nodes now offer the storage driver choice, so the
RAG page no longer claims it is only asked while creating a RAG with .rag.

Also documents that a duckdb RAG is two files that must travel together, what
Coyote does when only the .yaml arrives, and that a local Qdrant is reached
without going through an ambient proxy.
2026-08-12 12:48:44 -06:00
Dark-Alex-17 6ad2c80680 docs: Document RAG storage drivers, Qdrant attach, and sandbox wiring
Covers the pluggable RAG driver work: the yaml/duckdb/qdrant drivers and how
to choose between them, attaching a read-only remote Qdrant collection with
.rag attach, the driver field on graph rag nodes, and how an attached RAG's
host and API key reach a sandbox.

Also corrects two statements the driver work invalidated: embeddings are no
longer necessarily in-memory, and .rebuild rag now re-embeds the whole corpus
rather than just accommodating document changes.
2026-08-11 21:12:20 -06:00
Dark-Alex-17 e290026b5e docs: Renamed user__ask to user__select 2026-07-23 18:53:36 -06:00
Dark-Alex-17 d02ab67f37 docs: Added documentation on the new reasoning effort fields 2026-07-16 12:56:28 -06:00
Dark-Alex-17 669187d148 docs: Updated docs to mention features about graph-based RAG 2026-07-13 17:00:22 -06:00
Dark-Alex-17 75de260e0e docs: Add the new graph agents, agents, and tools used for the improved sisyphus system 2026-07-04 13:12:44 -06:00
Dark-Alex-17 f6b0850139 docs: updated docs with skill documentation in forgotten places 2026-06-08 11:45:54 -06:00
Dark-Alex-17 1e8a53c014 docs: added docs for the new and improved sisyhpus agent system 2026-06-02 14:02:27 -06:00
Dark-Alex-17 2cbefe74e3 docs: documented graph-based agent llm skills usage 2026-06-02 12:45:13 -06:00
Dark-Alex-17 217be7684e docs: added explicit mention to not add user interaction via custom tools or script nodes for graph execution 2026-05-27 15:26:43 -06:00
Dark-Alex-17 cea15233ac Update Loki to Coyote 2026-05-27 12:54:06 -06:00
Dark-Alex-17 687b0abb32 docs: updated graph agent docs to reflect improved llm node failure behavior 2026-05-22 18:33:35 -06:00
Dark-Alex-17 a0fda62bb4 docs: added environment variable documentation for script nodes 2026-05-21 13:31:58 -06:00
Dark-Alex-17 732d43e298 docs: updated docs with a cross-branch read gotcha 2026-05-20 19:01:01 -06:00
Dark-Alex-17 c88b5be6da docs: Updated the graph agents docs to discuss parallelization and clarify fan-out 2026-05-20 16:49:23 -06:00
Dark-Alex-17 ec7e6eb438 docs: updated the GraphAgent wiki to reference a general deep_research agent instead of LOINC stuff 2026-05-18 15:59:32 -06:00
Dark-Alex-17 6e08cfd984 docs: created docs for the new graph agent system 2026-05-18 15:37:53 -06:00