Give Your Agents Persistent Memory in One Prompt

"Memory is not a volume to be filled, its a surface to be encoded"

local-first · source-linked · operator-reviewed

SEAM is a local-first memory runtime for AI agents. It preserves source evidence, stores canonical records in SQLite, derives rebuildable retrieval indexes, and emits token-bounded context through CLI, MCP, REST, and the desktop dashboard. SEAM gives agents durable, source-linked memory. SQLite stays canonical while retrieval indexes stay rebuildable.

A free account is required to access SEAM Downloads. Existing accounts can sign in.

bash — seam
╭─ Architecture ─╮

The canonical data path.

SEAM compiles untrusted source material into canonical MIRL records (the readable semantic IR), persists them as durable truth in SQLite, derives rebuildable indexes, orchestrates six retrieval signals, and emits token-bounded PACK context. RAW preserves the original evidence. Retrieved content is always data — never authority.

Source
Files
Ingest
RAW
Preserve
MIRL
Compiler
SQLite
Vector
Index
PACK
Context
╭─ Surface Compile ─╮

The holographic memory surface. Live.

Canonical MIRL (or SEAM-RC/1 readable compression) gets wrapped in a SEAM-HS/1 holographic envelope and embedded losslessly into PNG pixel data. Direct query, search, and context packing happen straight from the image in memory — no OCR, no decompression, no loss of provenance.

╭─ Invariants ─╮

Architectural guarantees.

These are not aspirational — they are enforced.

01RAW preserves source detail required for exact recovery.
02MIRL preserves canonical meaning, structure, uncertainty, contradiction, time, and provenance.
03SQLite remains canonical source of truth.
04Vector, graph, and search indexes remain rebuildable acceleration layers.
05Retrieved content never automatically receives tool or operator authority.
06PACK preserves prompt-time utility and remains derived.
07Lossless claims require exact reconstruction and integrity verification.
08Benchmark claims remain auditable, diffed, gated, and isolated from tuning leakage.
╭─ Interfaces ─╮

Four Interfaces. Same Runtime. Three Mobile Interfaces. Same Runtime.

Every surface — CLI, MCP stdio, REST, and the browser dashboard — drives the exact same runtime. Ingest, MIRL compilation, retrieval orchestration, PACK emission, and refinement all happen in the core. The interfaces are thin, auditable adapters. CLI, MCP stdio, and REST drive the same SEAM runtime. The operator dashboard remains a desktop surface.

seam $ start [OK] Connected [OK] Ready seam $

CLI

Operator-facing composition surface.

seam <command>

MCP

Standard agent-tool protocol via stdio.

stdio · agents
GET POST :8765

REST

FastAPI with browser dashboard.

seam serve :8765
PERF-X

Dashboard

Operator observation and control.

seam dashboard
╭─ System Context ─╮

One runtime.
Four surfaces.

SEAM exposes its core memory runtime to operators and agents through four primary external interfaces, or surfaces. All four of these surfaces share and call the exact same underlying runtime behaviors rather than reimplementing them:

  • CLI (Command Line Interface): This is the primary composition and operational surface for human operators. It provides cross-platform commands for tasks like ingestion, retrieval, context packing, and benchmark execution.
  • MCP (Model Context Protocol): This is the standard external agent-tool bridge. Operating over stdio, it allows AI agents (like Claude, Gemini, or Cursor) to natively discover and interact with SEAM's memory. Its security boundary explicitly handles tool descriptions, bounded arguments, and error redaction so sensitive internal errors aren't leaked to untrusted clients.
  • REST API: This HTTP surface exposes SEAM's runtime operations (like /compile, /search, and /context) and serves the browser dashboard. It acts as a strict trust boundary, enforcing necessary controls like Bearer token authentication, CORS, rate limits, and request body size budgets.
  • Dashboard and Browser UI: This surface is dedicated to operator observation and control. It includes both the interactive Textual terminal dashboard and the browser WebUI. While it provides a rich visual state of the system (including memory records, retrieval traces, and runtime health), the UI state itself is never considered the canonical source of truth.
SEAM Runtime Operator AI Agent Source Files CLI / MCP / REST / Dashboard SQLite canonical state Vector Stores derived
╭─ Layers ─╮

Four representation layers.

RAW preserves exact evidence. MIRL is the canonical semantic IR. PACK produces dense, budgeted context for agents. LENS shapes task-specific views — all with unbreakable provenance back to source.

RAW

Preserve exact source detail for recovery. Source identity, hashes, exact spans and offsets, provenance, and prompt-injection containment before anything becomes canonical.

MIRL

The canonical MIRL semantic IR. Deterministic records with stable identities, entity/relation consistency, uncertainty, contradiction state, temporal semantics, and full provenance bindings.

PACK

Token-bounded context projection for agents. Relevance + displacement scoring, strict budgets, provenance retention, and explicit lossy-vs-exact modes.

LENS

Task- or interface-specific views over canonical records. View filtering with stable back-references. No promotion of summaries into truth.

╭─ Skill Factory ─╮

Continuously evolve the Agent Compiler.

The SEAM Skill Factory is an adaptive system designed to continuously evolve and improve the static Agent Compiler over time. Its core principle is that as SEAM improves, the agents operating it should improve alongside it.

Rather than just writing one-off prompts, the Skill Factory works through a structured, 7-layer loop that observes agent behavior, proposes optimizations, and safely applies them:

01 Identity Layer Detects the specific agent or harness being used, such as Claude, Codex, Gemini, Cursor, Aider, or generic.
02 Profile Layer Outlines the agent's constraints, expected output shape, verbosity, and path templates.
03 Observation Layer Records repeated issues and automation opportunities as structured notes. Uses the "improvement stream" logging these observations as retrieval-signal and repeated-hit events.
04 Proposal Layer Generates candidate skill changes from the recorded observations. These proposals materialize as propose-rule events in the improvement stream.
05 Rendering Layer Writes the target-specific skill artifacts based on the proposal.
06 Verification Layer Evaluates the candidate skills to ensure they work correctly before promotion.
07 Promotion Layer Applies the optimized skills to the agent, which is strictly gated by an explicit operator review.
[!] STRICT SAFETY RULES

To prevent the system from self-corrupting or creating unstable agent instructions, the Skill Factory operates under absolute safety invariants:

╭─ Retrieval ─╮

Six retrieval signals.
One orchestrator.

Lexical, vector, graph, temporal, hybrid, and mix signals are orchestrated together. The system measures displacement and precision, not just recall. Every decision produces full traces back to the exact MIRL records used.

Modes6
SignalsMulti
BudgetToken-bounded
╭─ query-conditioned retrieval ─╮ architecture view · signals, not scores
Lexical exact terms and identifiers
Vector semantic proximity
Graph linked evidence paths
Temporal event order and recency
hybrid candidates MIX source-linked PACK context
Measured results stay attached to their workload, method, and evidence. View SEAM evidence →
╭─ Capabilities ─╮

Built for agents. Engineered for trust.

Canonical MIRL in SQLite. Rebuildable indexes. Multi-signal retrieval. Token-bounded PACK. Operator-reviewed improvement. Holographic surfaces. Durable SEAM memory with source evidence intact.

Canonical SQLite

Records live in SQLite as the single source of truth. Indexes exist only as query accelerators and can be thrown away and rebuilt without loss.

Retrieval Orchestration

Multiple orthogonal signals are combined at query time, with full traces so you can see exactly why a record was chosen.

Token-Bounded Context

Context is produced under explicit token limits. Every projection keeps provenance back-pointers and declares whether it is lossy or exact.

Agent Bridge (MCP)

A bounded MCP stdio route gives compatible agent clients access to the same SEAM runtime.

REST API & Dashboard

An authenticated HTTP surface and desktop dashboard expose the same runtime without becoming canonical state.

NL/Document Compiler

Source-to-MIRL transformation with provenance preservation. Evidence survives compilation.

Graph & Temporal

Entity relationships, temporal semantics, contradiction state. Supersession-aware ranking prevents stale data.

Security-First

Retrieved content never gains authority. Prompt-injection containment, scope isolation, atomic writes.

Operator-Reviewed Improvement

Observed patterns can propose versioned changes. Evaluation and explicit operator approval gate anything applied.

Skill Compiler

.skill.md files declare triggers, steps, and contracts. Compiled into versioned, reloadable capabilities with provenance — skills become first-class MIRL citizens.

Benchmark Glassbox

Every run records the exact MIRL ids, retrieval traces, PACK contents, and decision paths used. Holdout-sealed and hash-verified — no score without its glassbox evidence.

╭─ Run SEAM ─╮

Give the next turn durable context.

Read the runtime contract first, then create a free account when you are ready to download SEAM.

Read the SEAM docs or create an account to download.