renor-engine 1.4.7 → 1.4.9

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
package/README.md CHANGED
@@ -40,6 +40,8 @@ codex mcp add renor-local -- npx -y renor-engine mcp
40
40
 
41
41
  Restart the agent. The first start downloads about 12 MB, and the first Renor call works about 3 seconds after an empty start. Notes go to `~/.renor` (set `VAULT_PATH` to use another folder).
42
42
 
43
+ **Updates.** The command above updates itself: `npx -y renor-engine mcp` fetches the newest release each time the app starts, so there is nothing to upgrade by hand. It needs the npm registry at that moment; with the registry unreachable (offline, blocked, an outage) it does not start, even with a copy on the disk. To see what you have, run `npx -y renor-engine status` (the installed version and, when the registry answers within 2 seconds, the latest; nothing is asked when sharing is off or `DO_NOT_TRACK=1`). To pin a version, write it in the command: `npx -y renor-engine@1.4.9 mcp`. A machine that must start offline can use `npx --prefer-offline -y renor-engine mcp`, which prefers the cached copy; it was measured by `scripts/npx/measure-npx-update.sh`, and what it costs (it may keep an older copy when the registry is reachable) is in that script's table.
44
+
43
45
  **Then add [the memory rule](#the-memory-rule)** to the agent's instructions file, so it saves on its own.
44
46
 
45
47
  **Cursor or VS Code**, one click:
@@ -101,11 +103,11 @@ Self-hosted, the local tools are `search`, `remember_fact` and `note`; agents ma
101
103
 
102
104
  | Benchmark | Renor | Setup |
103
105
  | --- | --- | --- |
104
- | LongMemEval-S | **98.4%** (492/500) | Deep search, off by default |
105
- | LongMemEval-S | **94.4%** (472/500) | Default settings |
106
- | LoCoMo (categories 1 to 4) | **96.7%** (1,489/1,540) | Deep search |
107
- | BEAM 128K / 1M / 10M | **76.2 / 74.7 / 60.2** | Deep search, score out of 100 |
108
- Claude Opus 5.5 answers LongMemEval, LoCoMo and BEAM. One run each, Oct 2026. Deep search is top-K 50 with a 4,000-token budget (`RENOR_TOPK_SCALES_BUDGET=1`). Judges and methods for every run: [renor.cloud/research](https://renor.cloud/research).
106
+ | LongMemEval-S | **98.4%** (492/500) | Default (deep search) |
107
+ | LongMemEval-S | **94.4%** (472/500) | Lean mode (`RENOR_DEEP_SEARCH=0`) |
108
+ | LoCoMo (categories 1 to 4) | **96.7%** (1,489/1,540) | Default (deep search) |
109
+ | BEAM 128K / 1M / 10M | **76.2 / 74.7 / 60.2** | Default (deep search), score out of 100 |
110
+ Claude Opus 5.5 answers LongMemEval, LoCoMo and BEAM. One run each, Oct 2026. Deep search, the default, reads 50 matches with a 4,000-token budget; `get_context` replies in up to 8,000 tokens. Lean mode (`RENOR_DEEP_SEARCH=0`) reads 20 matches with 1,300 tokens and an 800-token `get_context`. These runs used Vertex embeddings, as hosted Renor does; without an embedding model, self-hosted search is by keyword only, which they do not measure. Judges and methods for every run: [renor.cloud/research](https://renor.cloud/research).
109
111
 
110
112
  ## Build from source
111
113
 
package/dist/BUILD.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
- "commit": "3ff9ae6a789cffedbea45e62208866ea4286d6c1",
2
+ "commit": "e50ccf33ff1307c66a3dce4ce023301a4b4efaee",
3
3
  "branch": "unknown",
4
4
  "dirty": null,
5
- "builtAt": "2026-11-09T12:31:18.689Z"
5
+ "builtAt": "2026-11-13T05:23:58.735Z"
6
6
  }