Skip to content

Code graph and memory for your coding agents, in one Rust program. For Claude Code, Codex, Cursor and any MCP client.

docs: the README's memory text says "pre-release" instead of the month

VikramLex9fbcc467cb77
diff --git a/README.md b/README.md
index 54357fe..2dbb06e 100644
--- a/README.md
+++ b/README.md
@@ -50,7 +50,7 @@
## Agent memory, compared
-In our October comparison with seven memory systems, Graphicle matched the accuracy of Hindsight 0.10.2 and beat that of Mem0 OSS 2.2.1 (the open-source library, not Mem0's hosted platform) on LoCoMo-10, and while ingesting made about 12 model calls per conversation, against about 160 for Hindsight and 332 for Mem0 (estimates per conversation; each system's total is exact). Labels: development sets; one open model (Qwen3.8-27B) as every system's reader, judge and model; a pre-release build of Graphicle.
+In a pre-release comparison with seven memory systems, Graphicle matched the accuracy of Hindsight 0.10.2 and beat that of Mem0 OSS 2.2.1 (the open-source library, not Mem0's hosted platform) on LoCoMo-10, and while ingesting made about 12 model calls per conversation, against about 160 for Hindsight and 332 for Mem0 (estimates per conversation; each system's total is exact). Labels: development sets; one open model (Qwen3.8-27B) as every system's reader, judge and model; a pre-release build of Graphicle.
| System | LoCoMo-10 accuracy, points [95% CI] | Model calls per conversation, ingesting (estimate) | Prompt tokens per conversation, ingesting (estimate) |
|---|---|---|---|
@@ -65,7 +65,7 @@ In our October comparison with seven memory systems, Graphicle matched the accur
On the two other development sets, LME-84 and BEAM-100K, Graphicle trailed none of the systems it was compared with. [Every score, with its method and caveats](docs/benchmarks.md#agent-memory-comparison-with-seven-memory-systems).
-Earlier, on 8 October, a pre-release build also ran three published protocols on GPT models. Under Mem0's own LoCoMo protocol (its prompts, GPT-5 as reader and judge), it scored 93.5%, against 91.6% in Mem0's published result files (paired difference +1.95 points [+0.55, +3.55]). On LongMemEval-S under the same protocol it scored 92.6%, against Mem0's 93.4%. Against Hindsight's published contexts, it tied with a GPT-5.4 reader (LoCoMo 90.4 vs 90.6, LongMemEval-S 94.6 vs 93.4) and with a GPT-4.1-mini reader on LoCoMo (86.4 vs 87.5), and trailed with GPT-4.1-mini on LongMemEval-S (85.8 vs 89.2). [Every GPT run, with its labels](docs/benchmarks.md#agent-memory-with-gpt-models-the-8-october-runs).
+Earlier pre-release evaluations also ran three published protocols on GPT models. Under Mem0's own LoCoMo protocol (its prompts, GPT-5 as reader and judge), it scored 93.5%, against 91.6% in Mem0's published result files (paired difference +1.95 points [+0.55, +3.55]). On LongMemEval-S under the same protocol it scored 92.6%, against Mem0's 93.4%. Against Hindsight's published contexts, it tied with a GPT-5.4 reader (LoCoMo 90.4 vs 90.6, LongMemEval-S 94.6 vs 93.4) and with a GPT-4.1-mini reader on LoCoMo (86.4 vs 87.5), and trailed with GPT-4.1-mini on LongMemEval-S (85.8 vs 89.2). [Every GPT run, with its labels](docs/benchmarks.md#agent-memory-with-gpt-models-early-pre-release-runs).
## Quick start
diff --git a/docs/benchmarks.md b/docs/benchmarks.md
index 458f9a1..c3aa872 100644
--- a/docs/benchmarks.md
+++ b/docs/benchmarks.md
@@ -1130,9 +1130,9 @@ decision rule.
them ended at their output limit. It made no embedding calls to the model
servers, because it embeds in its own process.
-## Agent memory with GPT models: the 8 October runs
+## Agent memory with GPT models: early pre-release runs
-Before the comparison above, on 8 October 2026, a pre-release build of Graphicle answered LoCoMo (1,540 questions) and LongMemEval-S (500 questions) through three published protocols, on Azure OpenAI models, as memory vendors publish their results:
+Before the comparison above, in early pre-release evaluations on 8 October 2026, a pre-release build of Graphicle answered LoCoMo (1,540 questions) and LongMemEval-S (500 questions) through three published protocols, on Azure OpenAI models, as memory vendors publish their results:
- **mem0:** Mem0's published prompts, with GPT-5 (2025-08-07) as reader and judge.
- **gpt54-common:** the Omni prompts, with GPT-5.4 (2026-03-05, medium reasoning) as reader and GPT-4o (2024-11-20) as judge. This is not an exact replication of Zep's setup.