Episodiq
Ambient episodic memory for AI agents. Zero dependencies.
Every interaction becomes an episode. Every episode leaves a trace.
Episodiq gives AI agents a threshold of awareness: they know that past episodes exist without knowing what was found. This epistemic gap prevents hallucination and forces grounded retrieval.
Coming soon. Star the repo for updates.
Features (planned)
- Zero runtime dependencies (stdlib only)
- Framework-agnostic (text in, text out)
- Epistemic guard prevents confabulation from episode titles
- Episode-centric memory (not just tasks — conversations, research, moments)
- Single JSON file storage
License
MIT
1 maintainer
Metadata
1 maintainer
Release files for episodiq 0.0.1
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| episodiq-0.0.1.tar.gz | 1.9 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| episodiq-0.0.1-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 4.4 kB
Release files / episodiq-0.0.1.tar.gz
| Download URL | episodiq-0.0.1.tar.gz |
|---|---|
| Size | 1.9 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
33e8633895741c84cfdef0ca19bada5d4a8befd5c3a91511000384f29d95c8a6
|
|
BLAKE2b-256 checksum How to use checksums |
65f528ef2c098bc0673ab7b90b1e7938ab61a2a75d964255100dad017f53e017
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.12.12
|
Release files / episodiq-0.0.1-py3-none-any.whl
| Download URL | episodiq-0.0.1-py3-none-any.whl |
|---|---|
| Size | 2.6 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
a23c5212f4f67eb9b6129373e187c480bcd424f8710bc15b6b4c743c6cc7b618
|
|
BLAKE2b-256 checksum How to use checksums |
18bb87f19e9951296a4e36a708ddd0e09dc2909d316b8f34b61d6fc78e380bd4
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.12.12
|
