coder.

Decision and code intelligence for AI agents.

Record every choice. Map every symbol. Surface both at the right time — as context, fine-tuning data, RL signal, or replay. Local-first. Host-neutral.

Works with Claude CodeCodex CLIClineGemini CLICursorHermes
ACT 1 · SAVE TOKENS
THE COST

Every token your agent burns figuring out what's around it is a token it can't burn on the actual problem.

Most agent failures trace to context. Too little, and it guesses. Too much, and it drowns. Forge fixes both directions: blast radius scopes the change to its real callers, sidecar-first projections replace raw source dumps with structured maps, and just-in-time hook injection surfaces the right decision on the turn it matters — not jammed into every prompt.

Project-scoped recall keeps other codebases out of this one. The ubiquitous language of your repo is in the agent's hands by the second turn.

100 memories. 60 seconds.

Install. Bootstrap. Your agent remembers everything.

ACT 2 · CARRY CONTEXT
DECISION INTELLIGENCE

Reconstruct every choice your agent made.

Forge captures the decision trajectory — what the agent considered, what it picked, what evidence it cited, what it deferred. Local-first, replayable, yours.

Decision Timeline

Every choice in order, with evidence, counter-evidence, and a path-score.

Decision Graph

Branch points, dead ends, the path actually taken vs the paths considered.

Counterfactual replay

Replay any decision with different evidence; see what the agent would do.

CODE INTELLIGENCE

Every suggestion grounded in your real code.

Forge maintains a live map of the codebase — symbols, imports, references, tests — that any agent can query before suggesting changes. No hallucinated symbols, no broken refactors.

Live symbol graph

find_symbol, references, imports, callers — instantly, scoped to the active project.

Sidecar-first

Code intelligence is read from local sidecar projections (CodeMap, GraphShard). No cloud upload, no API key, no hosted index.

Blast radius

See every caller and every linked decision before you change a function.

Underneath: 8-layer Manas memory. Above: decision intelligence and code intelligence.

The memory grooms itself. Consolidator phases dedup near-duplicates, decay irrelevant memories, link related ones, and detect contradictions — so what gets recalled is curated, not just stored.

Spawn a team. Watch the team's decision graph. Replay the team. Forge tracks parent-child agent relationships across hosts so multi-agent runs are inspectable end-to-end.

STUDIO

Inspect what your agents are doing.

Forge Studio is the web-first control plane served by the daemon over HTTP/SSE. See live decision timelines, code graphs, memory layers, and agent sessions across hosts. Local-first, no cloud auth.

Decision timeline view

Live replay of every step, with scoring + evidence inline.

Code map browser

Navigate symbols, references, and impacted callers with one click.

Cross-host visibility

See Claude Code, Codex, Cline, Cursor, Hermes activity unified in one pane.

AUDITABILITY

Your data. Your machine. One file.

No account. No cloud. No trust required.

Single SQLite file on YOUR disk

No cloud. No telemetry. No account for free tier.

You own the file. Delete it. Move it. Back it up.

Bring your own model for air-gapped operation.

HOST-NEUTRAL

Your agents come and go. Forge stays.

One daemon serves Claude Code, Codex, Cline, Cursor, Gemini CLI, and Hermes — the same memory and decisions are visible to all of them. Switch agents mid-task and the next one picks up where the last one left off.

Models change every quarter. Your work doesn't restart.

Claude Code Codex CLI Cline Cursor Gemini CLI Hermes
ACT 3 · IMPROVE THE LOOP
WHAT THIS UNLOCKS

Smarter agents, every loop.

Every trajectory your agent produces is structured data. Use it.

Decision and code intelligence are the substrate. Use them however you want.

Smarter context

Recall + decision graph in the next prompt.

Smarter code

Every suggestion grounded in your real symbols.

Smarter training

Exportable, scored, privacy-safe trajectories for fine-tuning, RL, distillation, or search-based optimization.

Smarter agents over time

The loop closes itself.

TOOLING FOR LLMS

  • Tool-routing models — pick the right tool sequence per (model, language, intent) from your trace data
  • Context compressors — predict what the agent will cite, prune the rest
  • Self-improving prompts — system-prompt gaps surface from failed-trajectory analysis
  • Eval generation — every successful trajectory becomes a labeled eval case

More in /docs#tooling-for-llms.

This is happening now.

The agent thinks. Forge does everything else.