mira-oss

Name: mira-oss
Author: taylorsatula

bytaylorsatula· 1 MCP server

Stars

473

Forks

How to install mira-oss?

taylorsatula/mira-oss

$git clone https://github.com/taylorsatula/mira-oss

Installs into the current project.

›Prefer a prompt? Paste this to your agent

Install & use

Install mira-oss by running `git clone https://github.com/taylorsatula/mira-oss`, then use it for the current task and follow its documentation at https://github.com/taylorsatula/mira-oss.

Files · 1

View on GitHub

README.md

1	<img width="1657" height="932" alt="ghheader" src="https://github.com/user-attachments/assets/11121c54-94d8-4c97-a823-2613658afe73" />
2
3	I had the idea to build a recipe generator that could incorporate my cuisine preferences. 10,000 scope creeps later MIRA is a comprehensive best-effort approximation of a continuous digital entity.
4
5	This is my TempleOS.
6
7	## Self-directed
8	Mira accomplishes the end goal of continuity and recall through a blend of asynchronous conversation processing akin to REM sleep and active self-directed context window manipulation. There is one conversation thread forever. There is no functionality to "start a new chat." This constraint forces facing the hard questions of how to build believable persistence within a framework (forward pass transformers) that is inherently ephemeral.
9
10	Active conversation history stays live while it is relevant. Older material collapses into first-person memories. If an active conversation gets too large before it naturally collapses, MIRA compresses older messages into one rolling continuation brief while leaving the most recent turns untouched.
11
12	### First-Person Memory
13	When a conversation segment collapses, Mira generates a first-person summary ("I debugged the IndexError in process_batch.py...") rather than third-person ("The assistant discussed debugging..."). Early on I noticed third-person summaries created epistemic distance: Mira read them as logs about someone else, not memories of work It actually did. Absolute timestamps ("On Jan 8") replace relative time ("Yesterday") because relative time becomes a lie the moment the sun sets.
14
15	When generating a new segment summary, the model sees the previous five summaries as context. This allows the new summary to reference what came before with hazy continuity: "Building on Tuesday's API work..." or "Continuing the recipe experiments from last week...". The result is a continuously advancing narrative in the conversation history that gracefully tails off into the past. Each summary knows vaguely where it came from without carrying the full weight of everything before it.
16
17	The current summary format produces a 3-4 sentence memory trace, a two-sentence precis, a short display title, and a complexity score. The trace is for remembering; the other fields keep the conversation manifest useful without stuffing the full history back into the context window.
18
19	## Memory
20	I have painstakingly designed Memory in MIRA so it can largely manage itself without human curation. You should not need to housekeep old memories (context rot). They [decay via formula](https://github.com/taylorsatula/mira-OSS/blob/main/lt_memory/scoring_formula.sql) unless they Earn Their Keep through access, explicit references, links to other memories and entities, or real temporal relevance. Decay runs on use-days rather than calendar days, so going on vacation does not make MIRA forget you.
21
22	Memories are discrete synthesized information that is passively loaded into the context window through semantic similarity, entity hubs, memory traversal, filtering, and reranking. Most memory recall happens before Mira generates a response, so It does not have to first notice that something is missing and decide to search for it. Mira can still manually use memory_tool when It needs an explicit search, wants to create or link a memory, or needs exact control over what is being recalled.
23
24	However, sometimes you just need big ole chunks of document-shaped text. Mira handles this aspect via the domaindoc_tool, which allows Mira & You to collaborate on stable encrypted documents that do not decay. Domaindocs have section-level version history, sharing, pinned sections, and nested subsections.
25
26	To mitigate token explosion in longform content MIRA is able to expand, collapse, and subsection these documents autonomously. When a domaindoc section is not in use MIRA "closes the drawer" and the body is no longer polluting the context window, but MIRA still sees its title, summary, a

6 picks

Type

mira-oss

bytaylorsatula· 1 MCP server

Stars

473

Forks

How to install mira-oss?

taylorsatula/mira-oss

$git clone https://github.com/taylorsatula/mira-oss

Installs into the current project.

›Prefer a prompt? Paste this to your agent

Install & use

Install mira-oss by running `git clone https://github.com/taylorsatula/mira-oss`, then use it for the current task and follow its documentation at https://github.com/taylorsatula/mira-oss.

Files · 1

View on GitHub

README.md

1	<img width="1657" height="932" alt="ghheader" src="https://github.com/user-attachments/assets/11121c54-94d8-4c97-a823-2613658afe73" />
2
3	I had the idea to build a recipe generator that could incorporate my cuisine preferences. 10,000 scope creeps later MIRA is a comprehensive best-effort approximation of a continuous digital entity.
4
5	This is my TempleOS.
6
7	## Self-directed
8	Mira accomplishes the end goal of continuity and recall through a blend of asynchronous conversation processing akin to REM sleep and active self-directed context window manipulation. There is one conversation thread forever. There is no functionality to "start a new chat." This constraint forces facing the hard questions of how to build believable persistence within a framework (forward pass transformers) that is inherently ephemeral.
9
10	Active conversation history stays live while it is relevant. Older material collapses into first-person memories. If an active conversation gets too large before it naturally collapses, MIRA compresses older messages into one rolling continuation brief while leaving the most recent turns untouched.
11
12	### First-Person Memory
13	When a conversation segment collapses, Mira generates a first-person summary ("I debugged the IndexError in process_batch.py...") rather than third-person ("The assistant discussed debugging..."). Early on I noticed third-person summaries created epistemic distance: Mira read them as logs about someone else, not memories of work It actually did. Absolute timestamps ("On Jan 8") replace relative time ("Yesterday") because relative time becomes a lie the moment the sun sets.
14
15	When generating a new segment summary, the model sees the previous five summaries as context. This allows the new summary to reference what came before with hazy continuity: "Building on Tuesday's API work..." or "Continuing the recipe experiments from last week...". The result is a continuously advancing narrative in the conversation history that gracefully tails off into the past. Each summary knows vaguely where it came from without carrying the full weight of everything before it.
16
17	The current summary format produces a 3-4 sentence memory trace, a two-sentence precis, a short display title, and a complexity score. The trace is for remembering; the other fields keep the conversation manifest useful without stuffing the full history back into the context window.
18
19	## Memory
20	I have painstakingly designed Memory in MIRA so it can largely manage itself without human curation. You should not need to housekeep old memories (context rot). They [decay via formula](https://github.com/taylorsatula/mira-OSS/blob/main/lt_memory/scoring_formula.sql) unless they Earn Their Keep through access, explicit references, links to other memories and entities, or real temporal relevance. Decay runs on use-days rather than calendar days, so going on vacation does not make MIRA forget you.
21
22	Memories are discrete synthesized information that is passively loaded into the context window through semantic similarity, entity hubs, memory traversal, filtering, and reranking. Most memory recall happens before Mira generates a response, so It does not have to first notice that something is missing and decide to search for it. Mira can still manually use memory_tool when It needs an explicit search, wants to create or link a memory, or needs exact control over what is being recalled.
23
24	However, sometimes you just need big ole chunks of document-shaped text. Mira handles this aspect via the domaindoc_tool, which allows Mira & You to collaborate on stable encrypted documents that do not decay. Domaindocs have section-level version history, sharing, pinned sections, and nested subsections.
25
26	To mitigate token explosion in longform content MIRA is able to expand, collapse, and subsection these documents autonomously. When a domaindoc section is not in use MIRA "closes the drawer" and the body is no longer polluting the context window, but MIRA still sees its title, summary, a

6 picks

Type

mira-oss

How to install mira-oss?

Related

mira-oss

How to install mira-oss?

Related