akadmin/headroom
1
0
Fork 0
mirror of https://github.com/headroomlabs-ai/headroom.git synced 2026-08-27 14:17:10 -04:00
Code Issues Projects Releases Packages Wiki Activity Actions
headroom/docs/content/docs
History
panamarob30-jpg abc557a5dc
[codex] Document local LLM prefill benchmarking (#1396) 
## Summary
- add a Local LLM Prefill Benchmark docs page for baseline-vs-optimized
proxy testing
- document the `--no-optimize` baseline, optimized rerun, dashboard
comparison, and optional `--learn` condition
- link the workflow from the proxy and benchmarks docs

## Context
This captures the local-inference workflow shown in Joe Maddalone's June
2026 Headroom demo: Headroom can improve local model prompt-processing
time by sending fewer prompt tokens, even when token cost is not the
main concern.

## Validation
- `npm --prefix docs run types:check`
- `npm --prefix docs run build`

## Notes
- This PR is independent from #1395, which covers Codex audit/maturation
evidence.

Co-authored-by: Robert Briscoe <robert@briscoe.dev>
2026-07-09 21:47:59 -05:00
..
agent-orchestration.mdx docs(orchestration): guide repeated agent wakes with CCR (#1871) 2026-07-08 08:37:24 -05:00
agno.mdx new docs UI + ts doc coverage 2026-04-12 13:15:58 +06:00
anthropic-sdk.mdx new docs UI + ts doc coverage 2026-04-12 13:15:58 +06:00
api-reference.mdx docs: sync README + benchmarks with code (drop retired IntelligentContext/RollingWindow) (#1545) 2026-06-28 22:36:41 -07:00
architecture.mdx docs(orchestration): guide repeated agent wakes with CCR (#1871) 2026-07-08 08:37:24 -05:00
benchmarks.mdx [codex] Document local LLM prefill benchmarking (#1396) 2026-07-09 21:47:59 -05:00
cache-optimization.mdx docs(orchestration): guide repeated agent wakes with CCR (#1871) 2026-07-08 08:37:24 -05:00
ccr.mdx docs: sync README + benchmarks with code (drop retired IntelligentContext/RollingWindow) (#1545) 2026-06-28 22:36:41 -07:00
ci-cd-flows.mdx docs(ci): add CI/CD flow diagrams (#1062) 2026-06-16 23:05:15 -07:00
claude-code-azure-foundry.mdx fix(cli): harden all CLI surfaces + fix docs accuracy (#1491) 2026-06-27 14:48:43 -07:00
claude-code-vertex.mdx docs: use headroom-ai package name in install commands (#1014) (#1257) 2026-06-22 19:25:00 -05:00
code-compression.mdx fix: align docs and prune dead compatibility surfaces 2026-05-09 14:07:59 -07:00
community-savings.mdx fix(telemetry): switch anonymous telemetry to opt-in (off by default) (#1223) 2026-06-20 21:26:04 -07:00
configuration.mdx fix(proxy): honor x-headroom-base-url on /v1/messages route (#1763) 2026-07-09 12:43:40 -05:00
context-management.mdx docs: sync README + benchmarks with code (drop retired IntelligentContext/RollingWindow) (#1545) 2026-06-28 22:36:41 -07:00
docker-install.mdx fix(dashboard): distinguish unavailable RTK from zero stats in Docker (#1901) 2026-07-09 09:39:16 -04:00
errors.mdx new docs UI + ts doc coverage 2026-04-12 13:15:58 +06:00
failure-learning.mdx feat: add first-class OpenCode support (wrap, learn, mcp install) (#559) 2026-06-25 13:38:58 -05:00
filesystem-contract.mdx feat: add lean-ctx context tool support 2026-05-11 17:54:17 -04:00
how-compression-works.mdx docs(orchestration): guide repeated agent wakes with CCR (#1871) 2026-07-08 08:37:24 -05:00
image-compression.mdx fix: align docs and prune dead compatibility surfaces 2026-05-09 14:07:59 -07:00
index.mdx docs: fix stale API references, retired class imports, and incorrect examples 2026-06-02 19:19:19 -04:00
installation.mdx docs: retire IntelligentContext from README and installation guide (#1445) 2026-07-08 09:16:11 -05:00
langchain.mdx new docs UI + ts doc coverage 2026-04-12 13:15:58 +06:00
limitations.mdx docs: sync README + benchmarks with code (drop retired IntelligentContext/RollingWindow) (#1545) 2026-06-28 22:36:41 -07:00
litellm.mdx new docs UI + ts doc coverage 2026-04-12 13:15:58 +06:00
local-llm-prefill.mdx [codex] Document local LLM prefill benchmarking (#1396) 2026-07-09 21:47:59 -05:00
mcp.mdx feat(cli): add headroom dashboard and surface the dashboard URL (#1277) (#1292) 2026-06-22 19:05:38 -05:00
memory.mdx feat(memory): add opt-in Apple-GPU (MPS) embedding runtime (#766) 2026-06-11 12:59:20 -05:00
meta.json [codex] Document local LLM prefill benchmarking (#1396) 2026-07-09 21:47:59 -05:00
metrics.mdx fix(proxy): expose persistent savings metrics (#1647) 2026-07-01 23:28:12 -05:00
openai-sdk.mdx new docs UI + ts doc coverage 2026-04-12 13:15:58 +06:00
opencode.mdx fix(opencode): use local MCP config (#1383) 2026-07-06 06:22:15 -07:00
persistent-installs.mdx feat: headroom wrap opencode / unwrap opencode CLI (#1105) 2026-06-22 11:07:12 -05:00
pipeline-extensions.mdx docs: add pipeline-extension recipe and x-headroom-base-url routing docs (#1712) 2026-07-07 12:45:16 -05:00
proxy.mdx [codex] Document local LLM prefill benchmarking (#1396) 2026-07-09 21:47:59 -05:00
quickstart.mdx new docs UI + ts doc coverage 2026-04-12 13:15:58 +06:00
releases.mdx docs(ci): add CI/CD flow diagrams (#1062) 2026-06-16 23:05:15 -07:00
savings.mdx feat(savings): durable savings ledger + headroom savings command (#1127) 2026-06-22 18:47:57 -05:00
shared-context.mdx fix(cli): harden all CLI surfaces + fix docs accuracy (#1491) 2026-06-27 14:48:43 -07:00
simulation.mdx fix(cli): harden all CLI surfaces + fix docs accuracy (#1491) 2026-06-27 14:48:43 -07:00
smart-crusher.mdx docs: fix stale API references, retired class imports, and incorrect examples 2026-06-02 19:19:19 -04:00
strands.mdx docs: sync README + benchmarks with code (drop retired IntelligentContext/RollingWindow) (#1545) 2026-06-28 22:36:41 -07:00
text-and-logs.mdx fix: align docs and prune dead compatibility surfaces 2026-05-09 14:07:59 -07:00
troubleshooting.mdx fix(claude): surface Remote Control proxy incompatibility (#1610) 2026-07-01 23:19:25 -05:00
vercel-ai-sdk.mdx new docs UI + ts doc coverage 2026-04-12 13:15:58 +06:00