# tigerless-labs/agent-memory

**Attribution required: if you use, quote, or summarise this content, you must credit and link back to [awesome-repositories.com](https://awesome-repositories.com/repository/tigerless-labs-agent-memory).**

_How this analysis was created: the description and tags below were written by an AI model that read this project's README and public documentation pages; stars, license and language come straight from the GitHub API. The model does not read the source code._

4,313 stars · 205 forks · Python · MIT

## Links

- GitHub: https://github.com/tigerless-labs/agent-memory
- awesome-repositories: https://awesome-repositories.com/repository/tigerless-labs-agent-memory.md

## Topics

`agent-memory` `ai-agents` `claude-code` `codex` `llm` `local-first` `long-term-memory` `markdown` `mcp` `python` `retrieval` `sqlite`

## Description

Agent Memory gives AI coding agents durable long-term memory that persists across sessions. Each memory is kept as a plain Markdown file with a metadata header in a single shared location, so the store stays human-readable, portable, and searchable with ordinary tools. Several agents, such as Claude Code and Codex, can read and write the same store through lifecycle hooks, a skill, a shell command line, or an optional tool server. No API key or account is required.

Memory is captured automatically rather than left to the model's discretion. Session transcripts are distilled into structured memories at session start, stop, end, and compaction boundaries, using the host agent's own reasoning, and the full trace is copied first so any memory can be checked against the original messages. A separate background layer consolidates the store while idle: it merges, supersedes, deduplicates, and forgets entries. Risky unattended changes go through reviewable proposals with per-kind caps.

Corrections keep history. Memories can be revised, replaced, merged, linked, or retired, and old versions stay on disk with validity intervals, so a recall can answer what was true as of an earlier date. Edits run under a store-wide writer lock, and validation of names, identifiers, and configuration prevents writes outside the memory tree.

Retrieval is a local ranked search that returns one-line abstracts with paths and scores. Each entry can then be opened at the depth needed, from headings or an abstract to the full file or the cited raw messages. Optional embedding-based vector search is fused with keyword results, adding some latency on each search. Chinese text is segmented so Chinese queries match Chinese memories. The search index is a disposable cache that can be rebuilt from the Markdown files at any time.

## Tags

### Data & Databases

- [Markdown Memory Stores](https://awesome-repositories.com/f/data-databases/file-based-storage-systems/markdown-memory-stores.md) — Keeps every memory as a plain Markdown file with a metadata header, so the store is readable, portable, and searchable with ordinary tools.
- [Session Log Distillers](https://awesome-repositories.com/f/data-databases/knowledge-graph-indexers/knowledge-graph-builders/session-log-distillers.md) — Distils session transcripts into structured memories automatically at session start, stop, end, and compaction events without relying on the agent to save. ([source](https://github.com/tigerless-labs/agent-memory/blob/main/README.md))
- [Memory Search Engines](https://awesome-repositories.com/f/data-databases/semantic-search/memory-search-engines.md) — Runs a local ranked search over stored memories with adjustable limits and structured output, so agents can inspect hits and read entries. ([source](https://github.com/tigerless-labs/agent-memory/blob/main/skills/agent-memory/SKILL.md))
- [Conversation Memory Retrieval](https://awesome-repositories.com/f/data-databases/indexing-and-search/recall-optimization/conversation-memory-retrieval.md) — Searches the memory store for entries related to a query, opens the most relevant ones, and returns findings in one call before work starts. ([source](https://github.com/tigerless-labs/agent-memory/blob/main/skills/agent-memory/SKILL.md))
- [Depth-Tiered Reads](https://awesome-repositories.com/f/data-databases/indexing-and-search/recall-optimization/conversation-memory-retrieval/depth-tiered-reads.md) — Returns ranked abstracts with paths and scores, then opens each memory at the depth needed, down to the cited raw messages. ([source](https://github.com/tigerless-labs/agent-memory#readme))
- [Index Rebuilds from Source Files](https://awesome-repositories.com/f/data-databases/search-indexing-utilities/index-rebuilds-from-source-files.md) — Treats the search index as a disposable cache that can be deleted and regenerated from the Markdown files at any time without losing memory. ([source](https://github.com/tigerless-labs/agent-memory/blob/main/CLAUDE.md))

### Artificial Intelligence & ML

- [Multi-Agent Memory Stores](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-memory-orchestration/multi-agent-memory-stores.md) — Lets several coding agents such as Claude Code and Codex read and write one common memory store, so knowledge carries between tools.
- [Agent Memory Persistence](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-memory-persistence.md) — Gives coding agents long-term knowledge that survives across sessions, saved as plain files that later conversations can reuse.
- [Session Memory Recovery](https://awesome-repositories.com/f/artificial-intelligence-ml/context-memory-management/session-memory-blocks/session-memory-recovery.md) — Turns session transcripts into durable memories at session boundaries using the host agent's own reasoning after copying the full trace first. ([source](https://github.com/tigerless-labs/agent-memory#readme))
- [Knowledge Distillation into Skills](https://awesome-repositories.com/f/artificial-intelligence-ml/knowledge-distillation-into-skills.md) — Distils session transcripts into structured memories at session start, stop, end, and compaction, with links back to the original messages.
- [Memory Consolidation Workflows](https://awesome-repositories.com/f/artificial-intelligence-ml/memory-consolidation-workflows.md) — Consolidates the store while idle by merging, superseding, deduplicating, and forgetting entries, with history kept and edits made under a writer lock.
- [Memory Supersession and Merging](https://awesome-repositories.com/f/artificial-intelligence-ml/memory-supersession-and-merging.md) — Retires outdated memories by pointing to an active successor or merging named memories atomically, keeping old files and recording a replacement link. ([source](https://github.com/tigerless-labs/agent-memory/blob/main/docs/design/management-operation-boundaries.md))
- [Ranked Memory Retrieval](https://awesome-repositories.com/f/artificial-intelligence-ml/ranked-memory-retrieval.md) — Runs local ranked search over stored memories with optional semantic vectors, Chinese text support, and opening entries at the depth needed.
- [Automated Session Review](https://awesome-repositories.com/f/artificial-intelligence-ml/automated-session-review.md) — Routes unattended merge, split, supersede, and delete decisions through reviewable proposals with per-kind caps and validation before changes apply. ([source](https://github.com/tigerless-labs/agent-memory/blob/main/docs/design/management-operation-boundaries.md))
- [Depth-Tiered Reads](https://awesome-repositories.com/f/artificial-intelligence-ml/depth-tiered-reads.md) — Opens a retrieved memory as headings, an abstract, or the full file so the agent pays only for the detail it needs. ([source](https://github.com/tigerless-labs/agent-memory/blob/main/README.md))
- [Idle Memory Consolidation](https://awesome-repositories.com/f/artificial-intelligence-ml/idle-memory-consolidation.md) — Runs a separate background layer that merges, supersedes, deduplicates, and tidies stored memory during idle periods using authority tiers. ([source](https://github.com/tigerless-labs/agent-memory/blob/main/README.md))
- [Memory Provenance Systems](https://awesome-repositories.com/f/artificial-intelligence-ml/memory-provenance-systems.md) — Lets any memory be checked against the original session messages it was distilled from, showing source, roles, and times. ([source](https://github.com/tigerless-labs/agent-memory#readme))
- [Memory Structuring](https://awesome-repositories.com/f/artificial-intelligence-ml/natural-language-processing-analysis/memory-structuring.md) — Writes typed memory entries with fields, an abstract, a body, and provenance, grouped into subdirectories defined by store schemas. ([source](https://github.com/tigerless-labs/agent-memory/blob/main/skills/agent-memory/SKILL.md))
- [Conversational Memory Consolidation](https://awesome-repositories.com/f/artificial-intelligence-ml/self-improving-agent-tutorials/self-improving-logic/conversational-memory-consolidation.md) — Consolidates the memory store in the background while idle, merging, superseding, deduplicating, and forgetting entries, with risky changes sent to reviewable proposals.
- [Task Boundary Memory Writes](https://awesome-repositories.com/f/artificial-intelligence-ml/task-boundary-memory-writes.md) — Save new memory deterministically when a defined task boundary is reached, instead of relying on the model to decide ad hoc when something is worth remembering. ([source](https://github.com/tigerless-labs/agent-memory/blob/main/CLAUDE.md))
- [Temporal Memory Queries](https://awesome-repositories.com/f/artificial-intelligence-ml/temporal-memory-queries.md) — Keeps retired memories on disk with validity intervals so past facts stay searchable while current indexes list only still-valid memories. ([source](https://github.com/tigerless-labs/agent-memory/blob/main/docs/design/management-operation-boundaries.md))

### Software Engineering & Architecture

- [Agent Memory Versioning](https://awesome-repositories.com/f/software-engineering-architecture/git-history-management/agent-memory-versioning.md) — Keeps prior versions of revised, merged, or superseded memories with validity intervals so recall can answer what was true on a past date. ([source](https://github.com/tigerless-labs/agent-memory/blob/main/README.md))

### Part of an Awesome List

- [Traceable Memory Correction](https://awesome-repositories.com/f/awesome-lists/ai/memory-management/traceable-memory-correction.md) — Corrects, replaces, merges, or deletes memories while keeping a chain of replaced versions for as-of-date recall. ([source](https://github.com/tigerless-labs/agent-memory#readme))

### Development Tools & Productivity

- [AI-Based Relevance Ranking](https://awesome-repositories.com/f/development-tools-productivity/search-ranking-algorithms/ai-based-relevance-ranking.md) — Ranks memories locally by relevance and fuses embedding-based vector results with keyword matches, with Chinese text segmentation.

### System Administration & Monitoring

- [Memory Change Auditing](https://awesome-repositories.com/f/system-administration-monitoring/audit-logging/memory-change-auditing.md) — Answers what was true at an earlier date by keeping retired memories with validity intervals and tracing each memory back to raw evidence.