whereismyai
Tigerless Agent Memory
Tigerless Agent Memory is a long-term memory runtime that provides persistent storage for AI agents using Markdown files as the source of truth and local retrieval.
This runtime provides long-term memory for AI agents by using Markdown files as a persistent source of truth. It stores information in a filesystem that remains readable and searchable by standard tools like grep, while an optional SQLite index handles ranking and retrieval. Because the system does not use a proprietary cloud database, the agent accesses stored memories as a local directory without network calls or external API keys. It supports integration with any agent capable of executing shell commands, including Claude Code, Codex CLI, and Muse Code. The system separates concerns by handling consolidation and distillation at conversation boundaries, allowing the agent to focus on tasks while keeping history structured and portable.
Tigerless Agent Memory at a glance
Key features
- Local ranked retrieval without API keys
- Markdown files as the primary source of truth
- Rebuildable SQLite index for fast lookup
- Automated distillation at conversation boundaries
- Hierarchical read access from abstract to raw material
- Git-able and greppable memory storage
- Atomic memory updates and record supersession
Use it for
- Storing persistent session history for coding agents
- Managing long-term context across disparate agent sessions
- Retaining project knowledge in a readable directory structure
- Enabling cross-agent memory sharing within a single store
Alternatives to Tigerless Agent Memory
- AI Memory — Shared memory for coding agents that works across machines and team members.
- Agentmemoryrepo — Enables agents to navigate memories like a wiki and share knowledge across sessions.
- Supermemory — Integrates long-term memory into AI coding agents with a single prompt.
- ReMe — It enables local-first, file-native long-term memory sharing across multiple AI agents.
- Memori — Reduces LLM token usage and spend by over 97% with targeted recall.
- MemOS — It delivers ultra-persistent memory, hybrid-retrieval, and token savings.
- TencentDB Agent Memory — It unifies cross-agent memory assets, skill libraries, wikis, and code graphs.
- Playground — Persists agent memory across sessions and searches by meaning.
- EverOS — It enables agents to learn from experience and improves over time without manual coding.
- LongMemory — Provides immutable, temporal, and governed recall instead of simple vector retrieval.
- memU — It gives every connected agent a shared and inspectable memory layer.
- Cognee — Persistent memory for AI agents using graph, vector, and relational retrieval.
All Tigerless Agent Memory alternatives