NousResearch/hermes-agent
Auto-summarize long contexts to reduce token usage
Cluster 480 · agent. Data as of
Nothing open on GitHub. Fix attempted, not merged.
The short answer
0open issues
0open PRs
5items grouped
- Known?
- Yes. 5 related items grouped here, 4 issues already closed.
- Fix event
- No fix has been merged to main. 1 PR closed without merging; see the attempts below.
- Tracker
- The maintainers' tracker marks this
unresolved. That is separate from the fix event. - Still open
- Nothing open on GitHub.
Next step: read the attempts below. Your case may extend or revive that work.
Pick up a Lab taskThese items concern automatically compressing or summarizing conversation history when context grows long, to reduce token consumption and support extended sessions. Approaches include saving summaries to file, LLM-based condensation, and self-triggered compaction after each turn.
Open issues0
Open PRs0
1 PR closed without merging
From the close comments: done elsewhere 1
-
#66533 feat: add self-triggered context compaction after each turn (#66501) · done elsewhere →
90f8414,#66501
Closed issues · 4
How this cluster was grouped
-
Link evidence (
partly structural links): some members are connected by structural evidence (shared changed files, or a closing/superseded reference); the rest are joined by an automated relevance judgement over their text. - Members outside that structural core may belong to a different underlying problem.
-
Pairwise link density
0.21: the share of item pairs that carry a link, counting a structural link in full and a relevance-only link at 0.36.1.00means every pair is linked.
Pick up a Lab task
Check whether a fix covers the open issues here, with your own agent. Bring back evidence for maintainers.
Open the LabAt a glance
- Subsystem
- agent
- Closed issues
- 4
- Attempts
- 1 PR closed without merging