This release is a pre-release and may not be stable for production use.
aglet-builtin-memory-summary
Rolling LLM-summarised conversation memory — the right Memory Technique for long chats where a sliding window would drop important context.
Part of the Aglet pluggable Agent runtime.
What it does
When the per-conversation buffer grows past trigger_chars, the technique
asks an LLM to compress the oldest half of the history into a single short
paragraph and recalls that summary on every subsequent turn. Recent turns are
kept verbatim.
Best combined with memory.sliding_window under routing: parallel_merge:
memory:
techniques:
- { name: sliding_window, config: { max_messages: 10 } }
- name: summary
config:
model: cheap
trigger_chars: 6000
keep_recent: 6
routing: parallel_merge
Install
pip install --pre aglet-builtin-memory-summary
Config
| Key | Default | Description |
|---|---|---|
model |
default |
Model alias (from agent.yaml models:) used for compression |
trigger_chars |
6000 |
Compress when the conversation buffer exceeds this many chars |
keep_recent |
6 |
Number of most-recent messages kept verbatim |
summary_prefix |
"[Prior conversation summary]" |
Label prepended to recalled summaries |
License
Apache-2.0
1 maintainer
Metadata
1 maintainer
Release files for aglet-builtin-memory-summary 0.1.0a1
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | |
|---|---|---|---|---|
| aglet_builtin_memory_summary-0.1.0a1.tar.gz | 3.8 kB | Without provenance | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| aglet_builtin_memory_summary-0.1.0a1-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 8.3 kB
Release files / aglet_builtin_memory_summary-0.1.0a1.tar.gz
| Download URL | aglet_builtin_memory_summary-0.1.0a1.tar.gz |
|---|---|
| Size | 3.8 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
0f9d6311e72903b2d3db05bcb9ae0c9a1be66d75ce6449d05a3e92966cefd487
|
|
BLAKE2b-256 checksum How to use checksums |
29c7b5a0d4e768d278890732e7464d263a3b7e84dcaeb2e33023a1392000e1dd
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.14.4
|
Release files / aglet_builtin_memory_summary-0.1.0a1-py3-none-any.whl
| Download URL | aglet_builtin_memory_summary-0.1.0a1-py3-none-any.whl |
|---|---|
| Size | 4.6 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
1e1da4288e4f2459bcde840a1d5f6df0eb8589abb935062a84581aa069f9f847
|
|
BLAKE2b-256 checksum How to use checksums |
143be3a3270d2af93edfbb394321eba73e13b3d860d1e98f1e901ed6bfdc8ca7
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.14.4
|
Security for aglet-builtin-memory-summary 0.1.0a1
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
